Search

Recent advancements in autonomous mobile robots have led to significant progress in area coverage tasks. However, challenges persist in optimizing the efficiency and computational complexity of complete coverage path planner (CCPP) algorithms for multi-robot systems, particularly in scenarios requiring revisiting or a double pass in specific locations, such as cleaning robots addressing spilled consumables. This paper presents an innovative approach to tackling the double-pass complete coverage problem using an autonomous inter-reconfigurable robot path planner. Our solution leverages a modified Glasius bio-inspired neural network (GBNN) to facilitate double-pass coverage through inter-reconfiguration between two robots. We compare our proposed algorithm with traditional multi-robot path planning in a centralized system, demonstrating a reduction in algorithm iterations and computation time. Our experimental results underscore the efficacy of the proposed solution in enhancing the efficiency of area coverage tasks. Furthermore, we discuss the implementation details and limitations of our study, providing insights for future research directions in autonomous robotics.

Abstract Floor cleaning robots are widely used in public places like food courts, hospitals, and malls to perform frequent cleaning tasks. However, frequent cleaning tasks adversely impact the robot’s performance and utilize more cleaning accessories (such as brush, scrubber, and mopping pad). This work proposes a novel selective area cleaning/spot cleaning framework for indoor floor cleaning robots using RGB-D vision sensor-based Closed Circuit Television (CCTV) network, deep learning algorithms, and an optimal complete waypoints path planning method. In this scheme, the robot will clean only dirty areas instead of the whole region. The selective area cleaning/spot cleaning region is identified based on the combination of two strategies: tracing the human traffic patterns and detecting stains and trash on the floor. Here, a deep Simple Online and Real-time Tracking (SORT) human tracking algorithm was used to trace the high human traffic region and Single Shot Detector (SSD) MobileNet object detection framework for detecting the dirty region. Further, optimal shortest waypoint coverage path planning using evolutionary-based optimization was incorporated to traverse the robot efficiently to the designated selective area cleaning/spot cleaning regions. The experimental results show that the SSD MobileNet algorithm scored 90% accuracy for stain and trash detection on the floor. Further, compared to conventional methods, the evolutionary-based optimization path planning scheme reduces 15% percent of navigation time and 10% percent of energy consumption.

Abstract Drain blockage is a crucial problem in the urban environment. It heavily affects the ecosystem and human health. Hence, routine drain inspection is essential for urban environment. Manual drain inspection is a tedious task and prone to accidents and water-borne diseases. This work presents a drain inspection framework using convolutional neural network (CNN) based object detection algorithm and in house developed reconfigurable teleoperated robot called ‘Raptor’. The CNN based object detection model was trained using a transfer learning scheme with our custom drain-blocking objects data-set. The efficiency of the trained CNN algorithm and drain inspection robot Raptor was evaluated through various real-time drain inspection field trial. The experimental results indicate that our trained object detection algorithm has detect and classified the drain blocking objects with 91.42% accuracy for both offline and online test images and is able to process 18 frames per second (FPS). Further, the maneuverability of the robot was evaluated from various open and closed drain environment. The field trial results ensure that the robot maneuverability was stable, and its mapping and localization is also accurate in a complex drain environment.

Floor-cleaning robots are becoming popular and operating in public places to ensure the places are clean and tidy. These robots are often operated in a dynamic environment that is less safe and has a high probability of ending up in accidents. Sound event-based context detection is expected to overcome drawbacks in a robot’s visual sensing to avoid a hazardous environment, especially in improper illumination and occlusion situations. Even though numerous studies in the literature discuss the benefits of sound-based context detection, there is no work reported related to context avoidance for cleaning robots. To this end, we propose a novel context avoidance framework based on a deep-learning method that can detect and classify a specific sound and localize the source from a robot’s frame to avoid that environment. The proposed model receives the spectrogram from the array of microphones as the input and produces two parallel outputs. The first output provides information about the spectrum class after running the classification task. The second output contains the localization message of the identified sound source. With the identity of the location that needs to be avoided, the proposed module will generate an alternative trajectory. The proposed model is evaluated in two real-world scenarios, wherein the model is trained to detect the escalator sound in the robot’s surroundings and avoid its location. In all considered scenarios, the developed system accomplished a significantly higher success rate in detecting and avoiding the escalator.

Hazardous object detection (escalators, stairs, glass doors, etc.) and avoidance are critical functional safety modules for autonomous mobile cleaning robots. Conventional object detectors have less accuracy for detecting low-feature hazardous objects and have miss detection, and the false classification ratio is high when the object is under occlusion. Miss detection or false classification of hazardous objects poses an operational safety issue for mobile robots. This work presents a deep-learning-based context-aware multi-level information fusion framework for autonomous mobile cleaning robots to detect and avoid hazardous objects with a higher confidence level, even if the object is under occlusion. First, the image-level-contextual-encoding module was proposed and incorporated with the Faster RCNN ResNet 50 object detector model to improve the low-featured and occluded hazardous object detection in an indoor environment. Further, a safe-distance-estimation function was proposed to avoid hazardous objects. It computes the distance of the hazardous object from the robot’s position and steers the robot into a safer zone using detection results and object depth data. The proposed framework was trained with a custom image dataset using fine-tuning techniques and tested in real-time with an in-house-developed mobile cleaning robot, BELUGA. The experimental results show that the proposed algorithm detected the low-featured and occluded hazardous object with a higher confidence level than the conventional object detector and scored an average detection accuracy of 88.71%.

Monitoring the safe social distancing then conducting efficient sterilization in potentially crowded public places are necessary but challenging especially during the COVID-19 pandemic. This work presents the 3D human space-based surveillance system enabling selective cleaning framework. To this end, the proposed AI-assisted perception techniques is deployed on Toyota Human Support Robot (HSR) equipped with autonomous navigation, Lidar, and RGBD vision sensor. The human density mapping represented as heatmap was constructed to identify areas with the level being likely the risks for interactions. The surveillance framework adopts the 3D human joints tracking technique and the accumulated asymmetrical Gaussian distribution scheme modeling the human location, size, and direction to quantify human density. The HSR generates the human density map as a grid-based heatmap to perform the safe human distance monitoring task while navigating autonomously inside the pre-built map. Then, the cleaning robot uses the levels of the generated heatmap to sterilize by the selective scheme. The experiment was tested in public places, including food court and wet market. The proposed framework performance analyzed with standard performance metrics in various map sizes spares about 19 % of the disinfection time and 15 % of the disinfection liquid usage, respectively.

Self-reconfigurable robots present advanced solutions for various automation applications in domains, e.g., planetary exploration, rescue missions, cleaning, and maintenance. These robots have the ability to change their morphology according to given requirements or adapt to new circumstances, which, for example, can overcome constraints while navigating within a working environment. However, the autonomous navigation of self-reconfigurable robots is more complex than that of robots with fixed shape because of the intrinsic complexity of robot motions, especially in complicated obstacle environments. To address this challenge, we present a novel path planning method for reconfigurable robots in this study. The technique is inspired by the similarity between a robot motion path and a heat conduction path at the steady-state. In the heat transfer analysis domain, feasible moving locations are modeled as materials with high conductivity, while obstacles are considered thermal insulators, and the initial and destination positions are assigned as heat sink and heat source, respectively. The temperature profile and gradient calculated by finite element analysis are used to indicate the possible moving directions from the heat sink to the heat source. Based on the temperature gradient ascent, a step-wise conductivity reaching algorithm is developed to optimize robot paths using customized multi-objective functions that take the costs of morphology changes, path smoothness, and safety into account. The proposed path planning method is successfully applied to the hinged-tetro self-reconfigurable robot and demonstrated on several virtual environments and a real-world testbed environment.

Reconfigurable robots have received broad research interest due to the high dexterity they provide and the complex actions they could perform. Robots with reconfigurability are perfect candidates in tasks like exploration or rescue missions in environments with complicated obstacle layout or with dynamic obstacles. However, the automation of reconfigurable robots is more challenging than fix-shaped robots due to the increased possible combinations of robot actions and the navigation difficulty in obstacle-rich environments. This paper develops a systematic strategy to construct a model of hinged-Tetromino (hTetro) reconfigurable robot in the workspace and proposes a genetic algorithm-based method (hTetro-GA) to achieve path planning for hTetro robots. The proposed algorithm considers hTetro path planning as a multi-objective optimization problem and evaluates the performance of the outcome based on four customized fitness objective functions. In this work, the proposed hTetro-GA is tested in six virtual environments with various obstacle layouts and characteristics and with different population sizes. The algorithm generates Pareto-optimal solutions that achieve desire robot configurations in these settings, with O-shaped and I-shaped morphologies being the more efficient configurations selected from the genetic algorithm. The proposed algorithm is implemented and tested on real hTetro platform, and the framework of this work could be adopted to other robot platforms with multiple configurations to perform multi-objective based path planning.

Routine cleaning the pavement is an essential requirement to maintain a sustainable environment for social life. The different width and type of pavements raise the challenges for autonomous vehicles with fixed shape to operate effectively. In this paper, we introduce the vision based reconfiguration of self-reconfigurable pavement sweeping robot called Panthera, which can adjust its frame width to ease the cleaning tasks to become friendly with different pavement geometry. The expansion and compression operations of the Panthera width are implemented by rotating one high torque motor connecting with the lead screw rod to change the opening angle of linkage hinges. The Panthera cleaning and locomotion operations are synchronized with changing the robot width according to the output of detected pavement width. To this end, the segmented pavement leveraged on the masked based deep convolutional neural network (DCNN) is used as input for the proposed closed-loop feedback control method, enabling the robot to adjust the requirement of changing the width during locomotion accurately. The proposed PID scheme takes into account the robot kinematic design with the flexibility of width changing modes. The experiments were carried out in real environments demonstrated the autonomous reconfiguration robot width with various locomotion scenarios on pavements of varying width.

Maintenance of ship hull involves routine tasks during dry-docking that includes inspection, paint stripping, and re-painting. Among those, paint stripping is always seen as harmful for human operators and a time-consuming task. To reduce human risk, cost, and environmental cleanliness, the shipping maintenance industries started using robotic solutions. However, most of such robotic systems cannot operate fully autonomous since it requires human in the loop to monitor the cleaning efficiency. To this end, a novel autonomous self-evaluating hull cleaning robot called Hornbill is presented in this paper. The proposed robot is capable of navigating autonomously on the hull surface and perform water jet blasting to strip off the paint coating. The robot is also enabled with a Deep Convolutional Neural Network (DCNN) based self-evaluating scheme that benchmarks cleaning efficiency. We evaluated the proposed robot's performance by conducting experimental trials on a metal plate under three different paint coatings. While performing the paint stripping task in every experimental trial, the self-evaluating scheme would generate the heat map that depicts the plate's cleanliness. The results indicate that the proposed self-evaluating system could successfully generate high accurate cleanliness heat maps in all considered scenarios, which simplifies the checkup process for paint inspectors.

Applying the automation in covering the areas entirely eases manual jobs in various domestic fields such as site investigation, search, rescue, security, cleaning, and maintenance. A self-reconfigurable robot with adjustable dimensions is a viable answer to improve the coverage percentage for predefined map areas. However, the shape-shifting of this robot class also adds to the complexity of locomotion components and the need for an optimal complete coverage strategy for this new type of robot. The typical complete coverage route, including the least times of shape-shifting, the shortest navigation route, and the minimum travel time, is presented in the article. By splitting the map into the sub-areas similar to the self-reconfigurable robot's available shapes, the robot can design the ideal tileset and optimal navigation strategies to cover the workspace. To this end, we propose a Complete Tileset Energy-Aware Coverage Path Planning (CTPP) framework for a tiling self-reconfigurable robot named hRombo with four rhombus-shaped modules. The robot can reconfigure its base structure into seven distinct forms by activating the servo motors to drive the three robot hinges connecting robot modules. The problem of optimal path planning assisting the proposed hRombo robot to clear optimally all predefined tiles within the arbitrary workspace is considered a classic Travel Salesman Problem (TSP), and this TSP is solved by the reinforcement learning (RL) approach. The RL's reward function and action space are based on robot kinematic and the required energies, including transformation, translation, and orientation actions, to move the robot inside the workspace. The CTPP for the hRombo robot is validated with conventional complete coverage methods in simulation and real workspace conditions. The results showed that the CTPP is suitable for producing Pareto plans that enable robots to navigate from source to target in different workspaces with the least consumed energy and time among considered methods.

Optimizing the coverage path planning (CPP) in robotics has become essential to accomplish efficient coverage applications. This work presents a novel approach to solve the CPP problem in large complex environments based on the Travelling Salesman Problem (TSP) and Deep Reinforcement Learning (DRL) leveraging the grid-based maps. The proposed algorithm applies the cellular decomposition methods to decompose the environment and generate the coverage path by recursively solving each decomposed cell formulated as TSP. A solution to TSP is determined by training Recurrent Neural Network (RNN) with Long Short Term Memory (LSTM) layers using Reinforcement Learning (RL). We validated the proposed method by systematically benchmarked with other conventional methods in terms of path length, execution time, and overlapping rate under four different map layouts with various obstacle density. The results depict that the proposed method outperforms all considered parameters than the conventional schemes. Moreover, simulation experiments demonstrate that the proposed approach is scalable to the larger grid-maps and guarantees complete coverage with efficiently generated coverage paths.

Pavement in outdoor settings is an unstructured environment with sharp corners, varying widths, and pedestrian activity that poses navigation challenges while cleaning for autonomous systems. In this work, an approach towards navigating without collision in constrained pavement spaces using the optimal instantaneous center of rotation (ICR) is demonstrated using an in-house developed omnidirectional reconfigurable robot named Panthera. The Panthera reconfigurable design results in varying footprints, supported by passive linear joints along the robot width, with locomotion and steering action using four wheels independent steering drive (4WISD). The robot kinematics and perception sensors system are discussed. Further, the ICR selection is carried out using multi-objective optimization, considering functions for steering, varying width, distance, and clearance to avoid a collision. The framework is incorporated in a local navigation planner and demonstrated experimentally in real pavement settings. The results with optimal selection of ICR in two dimensional space within the robot footprint successfully perform smooth navigation in the constraint space. It is experimentally highlighted with four different scenarios, i.e., constraint conditions encountered by a robot during navigation. Moreover, the formulation of optimal selection of ICR while avoiding collision is generic and can be used for other mobile robot architectures.

Extensive studies regarding complete coverage problems have been conducted, but a few tackle scenarios where the mobile robot is equipped with reconfigurable modules. The reconfigurability of these robots creates opportunities to develop new navigation strategies with higher dexterity; however, it also simultaneously adds in constraints to the direction of movements. This paper aims to develop a valid navigation strategy that allows tetromino-based self-reconfigurable robots to perform complete coverage tasks. To this end, a novel graph theory-based model to simulate the workspace coverage and make use of dynamic programming technique for optimal path searching and adaptive robot morphology shifting algorithms is proposed. Moreover, the influence of algorithms starting variables on workspace coverage outcome is analyzed thoughtfully in this paper. The simulation results showed that the proposed method is capable of generating navigation paths throughout the workspace, which ensures complete workspace coverage while minimizing the total number of actions performed by the robot.

Cebrenus Rechenburgi, a member of the huntsman spider family have inspired researchers to adopt different locomotion modes in reconfigurable robotic development. Object-of-interest perception is crucial for such a robot to provide fundamental information on the traversed pathways and guide its locomotion mode transformation. Therefore, we present a object-of-interest perception in a reconfigurable rolling-crawling robot and identifying appropriate locomotion modes. We demonstrate it in Scorpio, our in-house developed robot with two locomotion modes: rolling and crawling. We train the locomotion mode recognition framework, named Pyramid Scene Parsing Network (PSPNet), with a self-collected dataset composed of two categories paths, unobstructed paths (e.g., floor) for rolling and obstructed paths (e.g., with person, railing, stairs, static objects and wall) for crawling, respectively. The efficiency of the proposed framework has been validated with evaluation metrics in offline and real-time field trial tests. The experiment results show that the trained model can achieve an mIOU score of 72.28 and 70.63 in offline and online testing, respectively for both environments. The proposed framework’s performance is compared with semantic framework (HRNet and Deeplabv3) where the proposed framework outperforms in terms of mIOU and speed. Furthermore, the experimental results has revealed that the robot’s maneuverability is stable, and the proposed framework can successfully determine the appropriate locomotion modes with enhanced accuracy during complex pathways.

(1) Background: To study the feasibility of developing finite element (FE) models of the whole lumbar spine using clinical routine multi-detector computed tomography (MDCT) scans to predict failure load (FL) and range of motion (ROM) parameters. (2) Methods: MDCT scans of 12 subjects (6 healthy controls (HC), mean age ± standard deviation (SD): 62.16 ± 10.24 years, and 6 osteoporotic patients (OP), mean age ± SD: 65.83 ± 11.19 years) were included in the current study. Comprehensive FE models of the lumbar spine (5 vertebrae + 4 intervertebral discs (IVDs) + ligaments) were generated (L1–L5) and simulated. The coefficients of correlation (ρ) were calculated to investigate the relationship between FE-based FL and ROM parameters and bone mineral density (BMD) values of L1–L3 derived from MDCT (BMDQCT-L1-3). Finally, Mann–Whitney U tests were performed to analyze differences in FL and ROM parameters between HC and OP cohorts. (3) Results: Mean FE-based FL value of the HC cohort was significantly higher than that of the OP cohort (1471.50 ± 275.69 N (HC) vs. 763.33 ± 166.70 N (OP), p < 0.01). A strong correlation of 0.8 (p < 0.01) was observed between FE-based FL and BMDQCT-L1-L3 values. However, no significant differences were observed between ROM parameters of HC and OP cohorts (p = 0.69 for flexion; p = 0.69 for extension; p = 0.47 for lateral bending; p = 0.13 for twisting). In addition, no statistically significant correlations were observed between ROM parameters and BMDQCT- L1-3. (4) Conclusions: Clinical routine MDCT data can be used for patient-specific FE modeling of the whole lumbar spine. ROM parameters do not seem to be significantly altered between HC and OP. In contrast, FE-derived FL may help identify patients with increased osteoporotic fracture risk in the future.

Mosquito-borne diseases can pose serious risks to human health. Therefore, mosquito surveillance and control programs are essential for the wellbeing of the community. Further, human-assisted mosquito surveillance and population mapping methods are time-consuming, labor-intensive, and require skilled manpower. This work presents an AI-enabled mosquito surveillance and population mapping framework using our in-house-developed robot, named ‘Dragonfly’, which uses the You Only Look Once (YOLO) V4 Deep Neural Network (DNN) algorithm and a two-dimensional (2D) environment map generated by the robot. The Dragonfly robot was designed with a differential drive mechanism and a mosquito trapping module to attract mosquitoes in the environment. The YOLO V4 was trained with three mosquito classes, namely Aedes aegypti, Aedes albopictus, and Culex, to detect and classify the mosquito breeds from the mosquito glue trap. The efficiency of the mosquito surveillance framework was determined in terms of mosquito classification accuracy and detection confidence level on offline and real-time field tests in a garden, drain perimeter area, and covered car parking area. The experimental results show that the trained YOLO V4 DNN model detects and classifies the mosquito classes with an 88% confidence level on offline mosquito test image datasets and scores an average of an 82% confidence level on the real-time field trial. Further, to generate the mosquito population map, the detection results are fused in the robot’s 2D map, which will help to understand mosquito population dynamics and species distribution.

Periodic inspection of false ceilings is mandatory to ensure building and human safety. Generally, false ceiling inspection includes identifying structural defects, degradation in Heating, Ventilation, and Air Conditioning (HVAC) systems, electrical wire damage, and pest infestation. Human-assisted false ceiling inspection is a laborious and risky task. This work presents a false ceiling deterioration detection and mapping framework using a deep-neural-network-based object detection algorithm and the teleoperated ‘Falcon’ robot. The object detection algorithm was trained with our custom false ceiling deterioration image dataset composed of four classes: structural defects (spalling, cracks, pitted surfaces, and water damage), degradation in HVAC systems (corrosion, molding, and pipe damage), electrical damage (frayed wires), and infestation (termites and rodents). The efficiency of the trained CNN algorithm and deterioration mapping was evaluated through various experiments and real-time field trials. The experimental results indicate that the deterioration detection and mapping results were accurate in a real false-ceiling environment and achieved an 89.53% detection accuracy.

Human visual inspection of drains is laborious, time-consuming, and prone to accidents. This work presents an AI-enabled robot-assisted remote drain inspection and mapping framework using our in-house developed reconfigurable robot Raptor. The four-layer IoRT serves as a bridge between the users and the robots, through which seamless information sharing takes place. The Faster RCNN ResNet50, Faster RCNN ResNet101, and Faster RCNN Inception-ResNet-v2 deep learning frameworks were trained using a transfer learning scheme with six typical concrete defect classes and deployed in an IoRT framework remote defect detection task. The efficiency of the trained CNN algorithm and drain inspection robot Raptor was evaluated through various real-time drain inspection field trials using the SLAM technique. The experimental results indicate that robot’s maneuverability was stable, and its mapping and localization were also accurate in different drain types. Finally, for effective drain maintenance, the SLAM-based defect map was generated by fusing defect detection results in the lidar-SLAM map.

Staircase cleaning is a crucial and time-consuming task for maintenance of multistory apartments and commercial buildings. There are many commercially available autonomous cleaning robots in the market for building maintenance, but few of them are designed for staircase cleaning. A key challenge for automating staircase cleaning robots involves the design of Environmental Perception Systems (EPS), which assist the robot in determining and navigating staircases. This system also recognizes obstacles and debris for safe navigation and efficient cleaning while climbing the staircase. This work proposes an operational framework leveraging the vision based EPS for the modular re-configurable maintenance robot, called sTetro. The proposed system uses an SSD MobileNet real-time object detection model to recognize staircases, obstacles and debris. Furthermore, the model filters out false detection of staircases by fusion of depth information through the use of a MobileNet and SVM. The system uses a contour detection algorithm to localize the first step of the staircase and depth clustering scheme for obstacle and debris localization. The framework has been deployed on the sTetro robot using the Jetson Nano hardware from NVIDIA and tested with multistory staircases. The experimental results show that the entire framework takes an average of 310 ms to run and achieves an accuracy of 94.32% for staircase recognition tasks and 93.81% accuracy for obstacle and debris detection tasks during real operation of the robot.

Routine rodent inspection is essential to curbing rat-borne diseases and infrastructure damages within the built environment. Rodents find false ceilings to be a perfect spot to seek shelter and construct their habitats. However, a manual false ceiling inspection for rodents is laborious and risky. This work presents an AI-enabled IoRT framework for rodent activity monitoring inside a false ceiling using an in-house developed robot called “Falcon”. The IoRT serves as a bridge between the users and the robots, through which seamless information sharing takes place. The shared images by the robots are inspected through a Faster RCNN ResNet 101 object detection algorithm, which is used to automatically detect the signs of rodent inside a false ceiling. The efficiency of the rodent activity detection algorithm was tested in a real-world false ceiling environment, and detection accuracy was evaluated with the standard performance metrics. The experimental results indicate that the algorithm detects rodent signs and 3D-printed rodents with a good confidence level.

Modern engineering problems require solutions with multiple functionalities in order to meet their practical needs to handle a variety of applications in different scenarios. Conventional design paradigms for single design purpose may not be able to satisfy this requirement efficiently. This paper proposes a novel system-of-systems bio-inspired design method framed in a solution-driven bio-inspired design paradigm. The whole design process consists of eight steps, that is, (1) biological solutions identification, (2) biological solutions definition/champion biological solutions, (3) principle extraction from each champion biological solution, (4) merging of extracted principles, (5) solution reframing, (6) problem search, (7) problem definition, and (8) principles application & implementation. The steps are elaborated and a case study of reconfigurable robots is presented following these eight steps. The design originates from the multimodal locomotion capabilities of two species (i.e., spiders and primates) and is analyzed based on the Pugh analysis. The resulting robotic platform could be potentially used for urban patrolling purposes.

Games and toys have been serving as entertainment tools to humans for a long period of time. While except for entertainment, they can also trigger inspiration and enhance productivity in many other domains such as healthcare and general workplaces. The concept of the game is referred to a series of structured procedures (e.g., card games) and virtual programs. The entertainment artifacts could be a toy or even a handicraft, such as origami and kirigami, for entertainment purposes in a broader sense. Recently, the design of robots and relevant applications in robotics has been emerging in taking inspiration from Games and Entertainment Artifacts (GEA). However, there is a lack of systematic and general process for implementing a GEA-inspired design for developing robot-related applications. In this article, we put forward a design paradigm based on the inspiration of game and entertainment artifacts which is a systematic design approach. The design paradigm could follow two different processes which are driven by problems and solutions, respectively, using analogies of games and entertainment artifacts to build robotic solutions for solving real problems. The problem-driven process starts with an existing real-world problem, which follows the sequences of robotics problem search, robotics problem identification, GEA solution search, GEA solution identification, GEA principle extraction, and the principle implementation. Reversely, the solution-driven process follows the sequence of GEA solution search, GEA solution identification, GEA principle extraction, robotics problem search, robotics problem identification, and principle implementation. We demonstrate the application of the design paradigm using the case study of a new type of reconfigurable floor cleaning robot and its path planning algorithm.

A novel robotic challenge, namely the robot inclusive spaces (RIS) challenge, is proposed in this paper, which is a cross disciplinary and design focused initiative. It aims to foster the roboticists, architects, and designers towards realizing robot friendly social spaces. Contrary to conventional robotics competitions focusing on designing robots and its component technologies, robot inclusive spaces challenge adopts an interdisciplinary “design for robots” strategy to overcome the traditional research problem in real world deployments of social robots. In order to realize the RIS, various architectural elements must be adapted including: design principles for inclusive spaces, lighting schemes, furniture choices and arrangement, wall and floor surfaces, pathways among others. This paper introduces the format and design principles of RIS challenge, presents a first run of the challenge, and gives the corresponding analysis.

Insect detection and control at an early stage are essential to the built environment (human-made physical spaces such as homes, hotels, camps, hospitals, parks, pavement, food industries, etc.) and agriculture fields. Currently, such insect control measures are manual, tedious, unsafe, and time-consuming labor dependent tasks. With the recent advancements in Artificial Intelligence (AI) and the Internet of things (IoT), several maintenance tasks can be automated, which significantly improves productivity and safety. This work proposes a real-time remote insect trap monitoring system and insect detection method using IoT and Deep Learning (DL) frameworks. The remote trap monitoring system framework is constructed using IoT and the Faster RCNN (Region-based Convolutional Neural Networks) Residual neural Networks 50 (ResNet50) unified object detection framework. The Faster RCNN ResNet 50 object detection framework was trained with built environment insects and farm field insect images and deployed in IoT. The proposed system was tested in real-time using four-layer IoT with built environment insects image captured through sticky trap sheets. Further, farm field insects were tested through a separate insect image database. The experimental results proved that the proposed system could automatically identify the built environment insects and farm field insects with an average of 94% accuracy.

The maintenance of ship hulls involves a series of routine tasks during dry-docking that renews its life-time and operating efficiency. One such task is hull inspection, which is always seen as harmful for human operators and a time-consuming task. The shipping maintenance industries started using the robotic solutions in order to reduce the human risk. However, most of such robotic systems cannot operate fully autonomously due to the fact that it requires humans in the loop. On the other hand, an autonomous hull inspection robot, called Sparrow, is presented in this paper. The proposed robot is capable of navigating autonomously on the vertical metal surface and it could perform metal thickness inspection. This article summarizes the robot’s mechanical design, system control, autonomy, and the inspection module. We evaluated the robot’s performance by conducting experimental trials on three different metal plates that varied in thickness. The results indicate that the presented robot achieves significantly better locomotion while climbing, and it can autonomously measure the metal thickness, which significantly reduces the human efforts in real-time.

Completed area coverage planning (CACP) plays an essential role in various fields of robotics, such as area exploration, search, rescue, security, cleaning, and maintenance. Tiling robots with the ability to change their shape is a feasible solution to enhance the ability to cover predefined map areas with flexible sizes and to access the narrow space constraints. By dividing the map into sub-areas with the same size as the changeable robot shapes, the robot can plan the optimal movement to predetermined locations, transform its morphologies to cover the specific area, and ensure that the map is completely covered. The optimal navigation planning problem, including the least changing shape, shortest travel distance, and the lowest travel time while ensuring complete coverage of the map area, are solved in this paper. To this end, we propose the CACP framework for a tiling robot called hTrihex with three honeycomb shape modules. The robot can shift its shape into three different morphologies ensuring coverage of the map with a predetermined size. However, the ability to change shape also raises the complexity issues of the moving mechanisms. Therefore, the process of optimizing trajectories of the complete coverage is modeled according to the Traveling Salesman Problem (TSP) problem and solved by evolutionary approaches Genetic Algorithm (GA) and Ant Colony Optimization (ACO). Hence, the costweight to clear a pair of waypoints in the TSP is defined as the required energy shift the robot between the two locations. This energy corresponds to the three operating processes of the hTrihex robot: transformation, translation, and orientation correction. The CACP framework is verified both in the simulation environment and in the real environment. From the experimental results, proposed CACP capable of generating the Pareto-optimal outcome that navigates the robot from the goal to destination in various workspaces, and the algorithm could be adopted to other tiling robot platforms with multiple configurations.

Periodic cleaning of all frequently touched social areas such as walls, doors, locks, handles, windows has become the first line of defense against all infectious diseases. Among those, cleaning of large wall areas manually is always tedious, time-consuming, and astounding task. Although numerous cleaning companies are interested in deploying robotic cleaning solutions, they are mostly not addressing wall cleaning. To this end, we are proposing a new vision-based wall following framework that acts as an add-on for any professional robotic platform to perform wall cleaning. The proposed framework uses Deep Learning (DL) framework to visually detect, classify, and segment the wall/floor surface and instructs the robot to wall follow to execute the cleaning task. Also, we summarized the system architecture of Toyota Human Support Robot (HSR), which has been used as our testing platform. We evaluated the performance of the proposed framework on HSR robot under various defined scenarios. Our experimental results indicate that the proposed framework could successfully classify and segment the wall/floor surface and also detect the obstacle on wall and floor with high detection accuracy and demonstrates a robust behavior of wall following.

This work presents a table cleaning and inspection method using a Human Support Robot (HSR) which can operate in a typical food court setting. The HSR is able to perform a cleanliness inspection and also clean the food litter on the table by implementing a deep learning technique and planner framework. A lightweight Deep Convolutional Neural Network (DCNN) has been proposed to recognize the food litter on top of the table. In addition, the planner framework was proposed to HSR for accomplishing the table cleaning task which generates the cleaning path according to the detection of food litter and then the cleaning action is carried out. The effectiveness of the food litter detection module is verified with the cleanliness inspection task using Toyota HSR, and its detection results are verified with standard quality metrics. The experimental results show that the food litter detection module achieves an average of 96 % detection accuracy, which is more suitable for deploying the HSR robots for performing the cleanliness inspection and also helps to select the different cleaning modes. Further, the planner part has been tested through the table cleaning tasks. The experimental results show that the planner generated the cleaning path in real time and its generated path is optimal which reduces the cleaning time by grouping based cleaning action for removing the food litters from the table.

Wall cleaning robots are developed to cater to the demands of the building maintenance sector. The ability to climb vertical surfaces is one of the crucial requirements of a wall cleaning robot. Robots that can climb vertical surfaces by adhesion to a surface are preferred since those do not require additional support structures. Vacuum suction mechanisms are widely used in this regard. The suction force acting on the robot due to the negative pressure built up is used by these robots for the adhesion. A robot will fall off or overturn when the pressure difference drops down a certain threshold. In contrast, if the pressure difference becomes too high, the excessive amount of frictional forces will hinder the locomotion ability. Moreover, a wall cleaning robot should be capable of adapting the adhesion force to maintain the symmetry between safe adhesion and reliable locomotion since adhesion forces which are too low or too high hinder the safety of adhesion and reliability of locomotion respectively. Thus, the pressure difference needs to be sustained within a desired range to ensure a robot’s safety and reliability. However, the pressure difference built up by a vacuum system may unpredictably vary due to unexpected variation of air leakages due to irregularities in surfaces. The existing wall cleaning robots that use vacuum suction mechanisms for adhesion are not aware of the adhesion status, or subsequently responding to them. Therefore, this paper proposes a design for a wall cleaning robot that is capable of adapting vacuum power based on the adhesion-awareness to improve safety and reliability. A fuzzy inference system is proposed here to adapt the vacuum power based on the variation of the adhesion and the present power setting of the vacuum. Moreover, an application of fuzzy logic to produce a novel controlling criterion for a wall cleaning robot to ensure safety and reliability of operation is proposed. A fuzzy inference system was used to achieve the control goals, since the exact underlying dynamics of the vacuum-adhesion cannot be mathematically modeled. The design details of the robot are presented with due attention to the proposed control strategy. Experimental results confirmed that the performance of a robot with proposed adhesion-awareness surpasses that of a robot with no adhesion-awareness in the aspects of safety, reliability, and efficiency. The limitations of the work and future design suggestions are also discussed.

Tiling robots with fixed morphology face major challenges in terms of covering the cleaning area and generating the optimal trajectory during navigation. Developing a self-reconfigurable autonomous robot is a probable solution to these issues, as it adapts various forms and accesses narrow spaces during navigation. The total navigation energy includes the energy expenditure during locomotion and the shape-shifting of the platform. Thus, during motion planning, the optimal navigation sequence of a self-reconfigurable robot must include the components of the navigation energy and the area coverage. This paper addresses the framework to generate an optimal navigation path for reconfigurable cleaning robots made of tetriamonds. During formulation, the cleaning environment is filled with various tiling patterns of the tetriamond-based robot, and each tiling pattern is addressed by a waypoint. The objective is to minimize the amount of shape-shifting needed to fill the workspace. The energy cost function is formulated based on the travel distance between waypoints, which considers the platform locomotion inside the workspace. The objective function is optimized based on evolutionary algorithms such as the genetic algorithm (GA) and ant colony optimization (ACO) of the traveling salesman problem (TSP) and estimates the shortest path that connects all waypoints. The proposed path planning technique can be extended to other polyamond-based reconfigurable robots.

This paper presents an approach to control rolling locomotion on the level ground with a biologically inspired hexapod robot. For controlling rolling locomotion, a controller which can compensate energy loss with rolling locomotion of the hexapod robot is designed based on its dynamic model. The dynamic model describes the rolling locomotion which is limited to planar one by an assumption that the hexapod robot does not fall down while rolling and influences due to collision and contact with the ground, and it is applied for computing the mechanical energy of the hexapod robot and a plant for a numerical simulation. The numerical simulation of the rolling locomotion on the level ground verifies the effectiveness of the proposed controller. The simulation results show that the hexapod robot can perform the rolling locomotion with the proposed controller. In conclusion, it is shown that the proposed control approach is effective in achieving the rolling locomotion on the level ground.

This article reports our findings from a robot-assisted therapeutic study conducted over 49 days to investigate the sociopsychological and physiological effects in children with autism spectrum disorder using a parrot-inspired robot, KiliRo, that we developed to help in therapeutic settings. We investigated the frequency of participants’ interactions among each other and assessed any changes in interaction using social network analysis. Interactions were assessed through manual observation before and after exposure to the robot. Urinary and salivary tests were performed to obtain protein and α-amylase levels, respectively, to report the physiological changes in participating children with autism spectrum disorder before and after interacting with the robot. This is a pioneering human–robot interaction study to investigate changes in stress levels using salivary samples. Systolic and diastolic blood pressure, heart rate, and arterial oxygen saturation level in blood were also monitored to investigate the physiological changes in participating children before, during, and after interacting with our parrot-inspired robot, KiliRo. The results show that the robot can help increase social interaction among children with autism spectrum disorder and assist in learning tasks. Furthermore, the clinical biochemistry test report using urinary and salivary samples indicates that the stress levels of children with autism reduced notably after interacting with the robot. Nevertheless, blood pressure, heart rate, and oxygen levels in blood did not show positive change in all participants.

hHoneycomb, a self-reconfigurable cleaning robot, is designed based on tiling theory, to overcome the significant challenges experienced by the fixed morphology cleaning robot. It consists of four regular hexagonal units and the units are connected by a planar revolute joint which helps in reconfiguration. This platform attains six distinct configurations (bar, bee, arch, wave, worm, and pistol) and these configurations have circular arcs and irregular concave and convex boundary that would help in accessing various obstacles in the cleaning space. This work addresses the mechanical design, system-level modeling, reconfiguration of the platform via hinged joint mechanism, mobility of the platform, polyhex based tiling set, and power consumption during reconfiguration. The strength of the mechanical structure is studied based on the structural analysis of the system using finite element method. Based on the natural frequency and deformation pattern, the proposed design is validated and proven to overcome structural failure and system resonance. The kinematics formulation of the platform during locomotion and dynamics of each block during reconfiguration are derived. The robotic system is modeled in Simscape multibody toolbox of Matlab and the mobility of the platform is studied using the numerical simulation. Based on the real-time current consumption of each joint during reconfiguration, the energy efficient configuration and tiling set are addressed.

As autonomous tiling devices begin to perform floor cleaning, agriculture harvesting, surface painting tasks, with minimal or no human intervention, a new challenge arises: these devices also need to be energy efficient and be constantly aware of the energy expenditure during deployments. Typical approaches to this end are often limited to fixed morphology robots with little or no consideration for reconfiguring class of robots. The main contribution of the paper is an energy estimation scheme that allows estimating the energy consumption when a tetromino inspired reconfigurable floor tiling robot, hTetro moves from one configuration to another for completing the area covering task. To this end, the proposed model applying the Newton-Raphson algorithm in combination with Pulse width modulation (PWM)-H bridge to characterize the energy cost associated with locomotion gaits across all valid morphologies and identify optimal area coverage strategy among available options is presented. We validate our proposed approach using an 8’ × 8’ square testbed where there exist 12 possible solutions for complete area coverage however with varying levels of energy cost. Then, we implemented our approach to our hTetro platform and conducted experiments in a real-life environment. Experimental results demonstrate the application of our model in identifying the optimal area coverage strategy that has the least associated energy cost.

The efficiency of energy usage applied to robots that implement autonomous duties such as floor cleaning depends crucially on the adopted path planning strategies. Energy-aware for complete coverage path planning (CCPP) in the reconfigurable robots raises interesting research, since the ability to change the robot’s shape needs the dynamic estimate energy model. In this paper, a CCPP for a predefined workspace by a new floor cleaning platform (hTetro) which can self-reconfigure among seven tetromino shape by the cooperation of hinge-based four blocks with independent differential drive modules is proposed. To this end, the energy consumption is represented by travel distances which consider operations of differential drive modules of the hTetro kinematic designs to fulfill the transformation, orientation correction and translation actions during robot navigation processes from source waypoint to destination waypoint. The optimal trajectory connecting all pairs of waypoints on the workspace is modeled and solved by evolutionary algorithms of TSP such as Genetic Algorithm (GA) and Ant Optimization Colony (AC) which are among the well-known optimization approaches of TSP. The evaluations across several conventional complete coverage algorithms to prove that TSP-based proposed method is a practical energy-aware navigation sequencing strategy that can be implemented to our hTetro robot in different real-time workspaces. Moreover, The CCPP framework with its modulation in this paper allows the convenient implementation on other polynomial-based reconfigurable robots.

This paper presents the bio-inspired design, realization, and validation of a reconfigurable rolling–crawling robot. The developed platform is able to mimic Cebrennus rechenbergi , a species of huntsman spider which can crawl and roll using only its legs. Mechanical design, control architecture, and actuator selection strategies targeting platform miniaturization are presented in detail. The navigating and autonomous capabilities of the robot are examined in two facets: (1) recovery behaviors where a robot in a previously unknown state after a fall recovers autonomously to a known standing gait state using Inertial Measurement Unit (IMU); and (2) terrain perception where the robot is capable of autonomously assessing the characteristics of the terrain and chooses the appropriate morphology and locomotion mode in relation to the perceived terrain.

Advancing an efficient coverage path planning in robots set up for application such as cleaning, painting and mining are becoming more crucial. Such drive in the coverage path planning field proposes numerous techniques over the past few decades. However, the proposed approaches were only applied and tested with a fixed morphological robot in which the coverage performance was significantly degraded in a complex environment. To this end, an A-star based zigzag global planner for a novel self-reconfigurable Tetris inspired cleaning robot (hTetro) presented in this paper. Unlike the traditional A-star algorithm, the presented approach can generate waypoints in order to cover the narrow spaces while assuming appropriate morphology of the hTtero robot with the objective of maximizing the coverage area. We validated the efficiency of the proposed planning approach in the Robot Operation System (ROS) Based simulated environment and tested with the hTetro robot in real-time under the controlled scenarios. Our experiments demonstrate the efficiency of the proposed coverage path planning approach resulting in superior area coverage performance in all considered experimental scenarios.

Extensive research has been conducted in human head pose detection systems and several applications have been identified to deploy such systems. Deep learning based head pose detection is one such method which has been studied for several decades and reports high success rates during implementation. Across several pet robots designed and developed for various needs, there is a complete absence of wearable pet robots and head pose detection models in wearable pet robots. Designing a wearable pet robot capable of head pose detection can provide more opportunities for research and development of such systems. In this paper, we present a novel head pose detection system for a wearable parrot-inspired pet robot using images taken from the wearer’s shoulder. This is the first time head pose detection has been studied in wearable robots and using images from a side angle. In this study, we used AlexNet convolutional neural network architecture trained on the images from the database for the head pose detection system. The system was tested with 250 images and resulted in an accuracy of 94.4% across five head poses, namely left, left intermediate, straight, right, and right intermediate.

Whilst Polyomino tiling theory has been extensively studied as a branch of research in mathematics, its application has been largely confined to multimedia, graphics and gaming domains. In this paper, we present a novel application of Tromino tiling theory, a class of Polyomino with three cells in the context of a reconfigurable floor cleaning robot, hTromo. The developed robot platform is able to automatically generate a global tiling set required to cover a defined space while leveraging on the Tromino tiling theory. Specifically, we validated the application of five Tromino tiling theorems with our hTromo robot. Experiments performed clearly demonstrate the efficacy of the proposed approach resulting in very high levels of area coverage performance in all considered experimental cases. This paper also presents the system architecture of our hTromo robot and a detailed description of the five tiling theorems applied in this study.

In the field of human-computer interaction, the Natural Goals, Operators, Methods, and Selection rules Language (NGOMSL) model is one of the most popular methods for modelling knowledge and cognitive processes for rapid usability evaluation. The NGOMSL model is a description of the knowledge that a user must possess to operate the system represented as elementary actions for effective usability evaluations. In the last few years, mobile robots have been exhibiting a stronger presence in commercial markets and very little work has been done with NGOMSL modelling for usability evaluations in the human-robot interaction discipline. This paper focuses on extending the NGOMSL model for usability evaluation of human-humanoid robot interaction in the soccer robotics domain. The NGOMSL modelled human-humanoid interaction design of Robo-Erectus Junior was evaluated and the results of the experiments showed that the interaction design was able to find faults in an average time of 23.84 s. Also, the interaction design was able to detect the fault within the 60 s in 100% of the cases. The Evaluated Interaction design was adopted by our Robo-Erectus Junior version of humanoid robots in the RoboCup 2007 humanoid soccer league.

Rather than the conventional classification method, we propose to divide modular and reconfigurable robots into intra-, inter-, and nested reconfigurations. We suggest designing the robot with nested reconfigurability, which utilizes individual robots with intra-reconfigurability capable of combining with other homogeneous/heterogeneous robots (inter-reconfigurability). The objective of this approach is to generate more complex morphologies for performing specific tasks that are far from the capabilities of a single module or to respond to programmable assembly requirements. In this paper, we discuss the theory, concept, and initial mechanical design of Hinged-Tetro, a self-reconfigurable module conceived for the study of nested reconfiguration. Hinged-Tetro is a mobile robot that uses the principle of hinged dissection of polyominoes to transform itself into any of the seven one-sided tetrominoes in a straightforward way. The robot can also combine with other modules for shaping complex structures or giving rise to a robot with new capabilities. Finally, the validation experiments verify the nested reconfigurability of Hinged-Tetro. Extensive tests and analyses of intra-reconfiguration are provided in terms of energy and time consumptions. Experiments using two robots validate the inter-reconfigur ability of the proposed module.

The Theo Jansen mechanism is gaining widespread popularity among the legged robotics community due to its scalable design, energy efficiency, low payload-to-machine-load ratio, bioinspired locomotion, and deterministic foot trajectory. In this paper, we perform for the first time the dynamic modeling and analysis on a four-legged robot driven by a single actuator and composed of Theo Jansen mechanisms. The projection method is applied to derive the equations of motion of this complex mechanical system and a position control strategy based on energy is proposed. Numerical simulations validate the efficacy of the designed controller, thus setting a theoretical basis for further investigations on Theo Jansen based quadruped robots.

We have developed a biologically inspired reconfigurable quadruped robot which can perform walking and rolling locomotion and transform between walking and rolling by reconfiguring its legs. This paper presents an approach to control rolling locomotion with the biologically inspired quadruped robot. For controlling rolling locomotion, a controller which can compensate robot’s energy loss during rolling locomotion is designed based on a dynamic model of the quadruped robot. The dynamic model describes planar rolling locomotion based on an assumption that the quadruped robot does not fall down while rolling and the influences of collision and contact with the ground, and it is applied for computing the mechanical energy and a plant in a numerical simulation. The numerical simulation of rolling locomotion on the flat ground verifies the effectiveness of the proposed controller. The simulation results show that the quadruped robot can perform periodic rolling locomotion with the proposed energy-based controller. In conclusion, it is shown that the proposed control approach is effective in achieving the periodic rolling locomotion on the flat ground.

As robots begin to perform jobs autonomously, with minimal or no human intervention, a new challenge arises: robots also need to autonomously detect errors and recover from faults. In this paper, we present a Support Vector Machine (SVM)-based fault diagnosis system for a bio-inspired reconfigurable robot named Scorpio. The diagnosis system needs to detect and classify faults while Scorpio uses its crawling and rolling locomotion modes. Specifically, we classify between faulty and non-faulty conditions by analyzing onboard Inertial Measurement Unit (IMU) sensor data. The data capture nine different locomotion gaits, which include rolling and crawling modes, at three different speeds. Statistical methods are applied to extract features and to reduce the dimensionality of original IMU sensor data features. These statistical features were given as inputs for training and testing. Additionally, the c-Support Vector Classification (c-SVC) and nu-SVC models of SVM, and their fault classification accuracies, were compared. The results show that the proposed SVM approach can be used to autonomously diagnose locomotion gait faults while the reconfigurable robot is in operation.

This paper puts forward the potential for designing a parrot-inspired robot and an indirect teaching technique, the adapted model-rival method (AMRM), to help improve learning and social interaction abilities of children with autism spectrum disorder. The AMRM was formulated by adapting two popular conventional approaches, namely, model-rival method and label-training procedure. In our validation trials, we used a semi-autonomous parrot-inspired robot, called KiliRo, to simulate a set of autonomous behaviors. A proposed robot-assisted therapy using AMRM was pilot tested with nine children with autism spectrum disorder for five consecutive days in a clinical setting. We analyzed the facial expressions of children when they interacted with KiliRo using an automated emotion recognition and classification system, Oxford emotion API (Application Programming Interface). Results provided some indication that the children with autism spectrum disorder appeared attracted and happy to interact with the parrot-inspired robot. Short qualitative interviews with the children’s parents, the pediatrician, and the child psychologist who participated in this pilot study, also acknowledged that the proposed parrot-inspired robot and the AMRM may have some merit in aiding in improving learning and social interaction abilities of children with autism spectrum disorder.

The need for a novel automated mosquito perception and classification method is becoming increasingly essential in recent years, with steeply increasing number of mosquito-borne diseases and associated casualties. There exist remote sensing and GIS-based methods for mapping potential mosquito inhabitants and locations that are prone to mosquito-borne diseases, but these methods generally do not account for species-wise identification of mosquitoes in closed-perimeter regions. Traditional methods for mosquito classification involve highly manual processes requiring tedious sample collection and supervised laboratory analysis. In this research work, we present the design and experimental validation of an automated vision-based mosquito classification module that can deploy in closed-perimeter mosquito inhabitants. The module is capable of identifying mosquitoes from other bugs such as bees and flies by extracting the morphological features, followed by support vector machine-based classification. In addition, this paper presents the results of three variants of support vector machine classifier in the context of mosquito classification problem. This vision-based approach to the mosquito classification problem presents an efficient alternative to the conventional methods for mosquito surveillance, mapping and sample image collection. Experimental results involving classification between mosquitoes and a predefined set of other bugs using multiple classification strategies demonstrate the efficacy and validity of the proposed approach with a maximum recall of 98%.

The field of Robotics is ever growing at the same time as posing enormous challenges. Numerous works has been done in biologically inspired robotics emulating models, systems and elements of nature for the purpose of solving traditional robotics problems. Chromatic behaviours are abundant in nature across a variety of living species to achieve camouflage, signaling, and temperature regulation. The ability of these creatures to successfully blend in with their environment and communicate by changing their colour is the fundamental inspiration for our research work. In this paper, we present dwarf chameleon inspired chromatic behaviour in the context of an autonomous surveillance robot, “PACHONDHI”. In our experiments, we successfully validated the ability of the robot to autonomously change its colour in relation to the terrain that it is traversing for maximizing detectability to friendly security agents and minimizing exposure to hostile agents, as well as to communicate with fellow cooperating robots.

Terrain perception greatly enhances the performance of robots, providing them with essential information on the nature of terrain being traversed. Several living beings in nature offer interesting inspirations which adopt different gait patterns according to nature of terrain. In this paper, we present a novel terrain perception system for our bioinspired robot, Scorpio, to classify the terrain based on visual features and autonomously choose appropriate locomotion mode. Our Scorpio robot is capable of crawling and rolling locomotion modes, mimicking Cebrenus Rechenburgi, a member of the huntsman spider family. Our terrain perception system uses Speeded Up Robust Feature (SURF) description method along with color information. Feature extraction is followed by Bag of Word method (BoW) and Support Vector Machine (SVM) for terrain classification. Experiments were conducted with our Scorpio robot to establish the efficacy and validity of the proposed approach. In our experiments, we achieved a recognition accuracy of over 90% across four terrain types namely grass, gravel, wooden deck, and concrete.

In recent decades, skyscrapers, as represented by the Burj Khalifa in Dubai and Shanghai Tower in Shanghai, have been built due to the improvements of construction technologies. Even in such newfangled skyscrapers, the façades are generally cleaned by humans. Wall climbing robots, which are capable of climbing up vertical surfaces, ceilings and roofs, are expected to replace the manual workforce in façade cleaning works, which is both hazardous and laborious work. Such tasks require these robotic platforms to possess high levels of adaptability and flexibility. This paper presents a detailed review of wall climbing robots categorizing them into six distinct classes based on the adhesive mechanism that they use. This paper concludes by expanding beyond adhesive mechanisms by discussing a set of desirable design attributes of an ideal glass façade cleaning robot towards facilitating targeted future research with clear technical goals and well-defined design trade-off boundaries.