Search

Industrial robots working in isolation in a highly automated system are valued for their high productivity. The shortcomings of these pure robotic cells become more apparent when flexibility in production is required to respond to varying production volumes and customized product demands. Complete automation is highly productive, but it is costly to set up and difficult to change. On the other hand, manual production, although flexible, is slower and prone to human errors. Hence, in industry, smarter automation methods that leverage the dexterity, flexibility, and decision-making capability of a human to speed, precision, and power of a robot are required. In industry, the need for flexibility in production has resulted in the acceptance of human–robot collaboration (HRC) as a viable alternative. The objective of this survey is to address the main challenges in HRC (safety, trust-in-automation, and productivity), safety measures, types of HRC, technical standards, and conceptual categorization of HRC: awareness, intelligence, and compliance.

Multi-step manipulation tasks in unstructured environments are extremely challenging for a robot to learn. Such tasks interlace high-level reasoning that consists of the expected states that can be attained to achieve an overall task and low-level reasoning that decides what actions will yield these states. We propose a model-free deep reinforcement learning method to learn multi-step manipulation tasks. We introduce a Robotic Manipulation Network (RoManNet), which is a vision-based model architecture, to learn the action-value functions and predict manipulation action candidates. We define a Task Progress based Gaussian (TPG) reward function that computes the reward based on actions that lead to successful motion primitives and progress towards the overall task goal. To balance the ratio of exploration/exploitation, we introduce a Loss Adjusted Exploration (LAE) policy that determines actions from the action candidates according to the Boltzmann distribution of loss estimates. We demonstrate the effectiveness of our approach by training RoManNet to learn several challenging multi-step robotic manipulation tasks in both simulation and real-world. Experimental results show that our method outperforms the existing methods and achieves state-of-the-art performance in terms of success rate and action efficiency. The ablation studies show that TPG and LAE are especially beneficial for tasks like multiple block stacking. Code is available at: https://github.com/skumra/romannet, Comment: Accepted for publication in IEEE Robotics and Automation Letters (RA-L)

In this work, we present a deep reinforcement learning based method to solve the problem of robotic grasping using visio-motor feedback. The use of a deep learning based approach reduces the complexity caused by the use of hand-designed features. Our method uses an off-policy reinforcement learning framework to learn the grasping policy. We use the double deep Q-learning framework along with a novel Grasp-Q-Network to output grasp probabilities used to learn grasps that maximize the pick success. We propose a visual servoing mechanism that uses a multi-view camera setup that observes the scene which contains the objects of interest. We performed experiments using a Baxter Gazebo simulated environment as well as on the actual robot. The results show that our proposed method outperforms the baseline Q-learning framework and increases grasping accuracy by adapting a multi-view model in comparison to a single-view model., 6 pages, 6 figures, 2020 IEEE International Conference on Automation Science and Engineering (CASE)

In this paper, a framework for monitoring human physiological response during Human-Robot Collaborative (HRC) task is presented. The framework highlights the importance of generation of event markers related to both human and robot, and also synchronization of data collected. This framework enables continuous data collection during an HRC task when changing robot movements as a form of stimuli to invoke a human physiological response. It also presents two case studies based on this framework and a data visualization tool for representation and easy analysis of the collected data during an HRC experiment., Comment: (First Draft) Accepted in IEEE SMC 2019

The sensor system presented in this article demonstrates the results of designing an exteroceptive sensing device for proximity sensing for collaborative robots. The intention of this design’s application is to develop an on-robot small footprint proximity sensing device. The design was assembled and put through a number of benchmark tests to validate the performance of the time-of-flight(ToF) sensor system when used in proximity sensing: Single Sensor Characterization, Sensor Overlap Characterization, and Sensor Ranging Under Motion. Through these tests, the ToF sensor ring achieves real time data throughput while minimizing blind spots.

Autonomous Navigation has been a field of major attraction to a large number of robotics enthusiasts all around the globe. Smart walker, a robot designed for assisting patients under intensive care, requires this exceptional add-on in order to have a better sense of the surrounding, captured through the RGB and depth sensor available on board. This paper addresses the navigation and mapping problem through a graph-based SLAM technique knows as Real-Time Appearance-based Mapping (RTAB-Map), which uses an interesting approach to map an area with the help of loop closures, and provides a number of visual feature tracking methods that can be used to detect the loop closures. The software stack on the Smart Walker has been built around ROS (Robot Operating System), and the necessary sensor, odometry and transformation messages have been configured accordingly, based on the onboard sensors and actuators attached to the Smart Walker. This paper discusses the implementation of RTAB-Map algorithm on the Smart Walker and steps involved in collecting a custom dataset. The approach also involves comparing the performance of visual feature tracking methods available in RTAB-Map algorithm on a standard dataset and on the custom dataset, based on non-statistical aspects in order to implement the right set of features for indoor use of the Smart Walker.

In this paper, a speed and separation monitoring (SSM) based safety controller using three time-of-flight ranging sensor arrays fastened to the robot links, is implemented. Based on the human-robot minimum distance and their relative velocities, a controller output characterized by a modulating robot operation speed is obtained. To avert self-avoidance, a self occlusion detection method is implemented using ray-casting technique to filter out the distance values associated with the robot-self and the restricted robot workspace. For validation, the robot workspace is monitored using a motion capture setup to create a digital twin of the human and robot. This setup is used to compare the safety,performance and productivity of various versions of SSM safety configurations based on minimum distance between human and robot calculated using on-robot Time-of-Flight sensors, motion capture and a 2D scanning lidar., Submitted to IEEE CASE 2019 (First Draft)

In this paper, an analysis of the sensing volume coverage of robot workspace as well as the shared human-robot collaborative workspace for various configurations of on-robot Time-of-Flight (ToF) sensor array rings is presented. A methodology for volumetry using octrees to quantify the detection/sensing volume of the sensors is proposed. The change in sensing volume coverage by increasing the number of sensors per ToF sensor array ring and also increasing the number of rings mounted on robot link is also studied. Considerations of maximum ideal volume around the robot workspace that a given ToF sensor array ring placement and orientation setup should cover for safe human robot interaction are presented. The sensing volume coverage measurements in this maximum ideal volume are tabulated and observations on various ToF configurations and their coverage for close and far zones of the robot are determined., Comment: (Draft) Submitted to IEEE SMC 2019

In this paper, a range sensing setup for performing detection and monitoring in an industrial robot workspace is presented. The setup uses a ring of Time-of-Flight laser range sensors mounted on a robot. A 3D simulation setup with the properties of the sensor mounted on a UR10 robot and a simple pick and place task with a human avatar is used to analyze its behavior and viability with industrial arm robots. Collision detection strategies based on human-robot separation distance and relative speeds are also implemented. These strategies are evaluated based on the human safety, robot performance and productivity of the task. The parameters and results of the experiments are tabulated. The results show the benefits of achieving dynamic awareness of the robot in comparison with the conventional methods used in industry. The development of the prototype sensor ring is also shown and the future work discussed.

14.1 System of autonomous rovers 366 14.1.1 Stationary sensors and sensor networks 367 14.2 Haptically controlled base robot 367 14.2.1 Electrical and mechanical construction 368 14.2.2 Haptic control: the haptic gravitational field (HGF) 369 14.2.3 Operation in the system of autonomous rovers 370 14.2.3.1 Communication schemes 370 14.2.3.2 Control schemes 371 14.3 Swarm robots 371 14.3.1 Mechanical construction and components 371 14.3.2 Navigation solution with GPS 372 14.3.2.1 The interface 372 14.3.2.2 Understanding the parameters 373 14.3.2.3 Calculating the heading angle 373 14.3.3 Sensor fusion 374 14.4 Application: robust threat monitoring 375 14.4.

A novel hexapod-quadcopter robot was developed with multicopter flight hardware directly embedded in the hexapod legs. This paper discusses the locomotion implementations for walking and flying in addition to transitional procedures necessary to switch between these two modes of operation. The algorithms were programmed using Robot Operating System on the 3D printed robot and tested to verify feasibility and performance.

Multicopter aircrafts are popular platforms for researching flight control and aerial image processing applications. These crafts could gain unique utility from the ability to fly to remote locations, land, then walk to perform close quarters operations in the area. This paper presents a novel hexapod-quadcopter design with multicopter flight hardware directly embedded in the hexapod legs. The robot is capable of terrestrial mobility as a hexapod and aerial mobility as a quadcopter. Aspects of the design are described along with pictures of the structural components, which were 3D printed.

In this paper, a framework for a system that will supervise the robot's action and behavior in the human-robot shared workspace is proposed. The function of the robot supervision system is to adaptively control the robot motion based on the human actions in order to optimize the productivity of a task while ensuring human safety. The real-time perception of the human action and environment will be done using a motion capture setup. The inspiration for the framework based on a human behavior model is explained. The aspect of human-robot interaction in an industrial setup is also discussed. An evaluation criteria of the proposed system in terms of safety, performance and productivity is also presented.

This paper proposes a novel leg design for a hu-manoid robot that can be 3D printed. More explicitly, the efforts of this paper are to bring some of the more complex leg designs seen in large scale bipedal robot into the realm of smaller bipeds while still allowing for it to be easily reproducible or modified. In order to accomplish this 3D printing technology was utilized, as well as an iterative design process. An ankle and knee powered by linear actuators were first constructed to test the conceptual design of the leg. This was followed by a complete leg design with improved ankle and knee. The results and challenges during the design process for actuation of the leg are discussed, and the electrical design is also explained.

Scan matching is a popular way of calculating a robot's position given range data corresponding to objects in the environment. This paper proposes a simultaneous localization and mapping algorithm that uses micro-particle swarm optimization as an alternative method to the traditional scan matching algorithms. The effectiveness of this algorithm is tested and compared to other popular simultaneous and localization algorithms.

Adaptable gaits are pivotal for allowing legged robots to navigate difficult terrain. One of the best gait styles to accomplish this goal is the rule-based free gait. First the forward and inverse kinematic solutions are solved for TigerBug, a circular hexapod. Then a rule based free gait is implemented on the circular hexapod in order to provide a platform for future rough terrain navigation.

In the every expanding field of robotics, mobile robots come in a two primary variations: wheeled and legged. This paper will focus on the latter, specifically a hexapod with a circular body that has its six legs distributed axisymmetrically around the body. The core goal of the project discussed here is to allow the robot to dynamically change foot placement based on an input vector in addition to controlling the position and orientation of the body. Specific attention is also given to a simulation model that can mimic this control of the robot in a virtual environment. Having a high level of control enhances the robot's ability to move in a very smooth and purposeful manner.

This work builds upon our previous work, where a swarm robot called a Groundscout was tested for its emergent behavior(s) using a system of systems framework based on discrete-event simulation and XML-based hardware in the loop simulation (HIL). This paper presents performance optimizations, bug-fixes, and implementations of new features to further examine the benefits of using HIL simulations to develop and test swarm robots. In this work, the Groundscout's communications protocols were improved, a new obstacle-avoidance algorithm was added, and the environment and simulation engines have been either re-implemented or optimized for performance. Specifically for the obstacle-avoidance algorithm, the benefits of using HIL simulations, together with the principle of model continuity, are clearly demonstrated with testing experiments. Towards the eventual goal of creating simulations for testing emergent behaviors of much larger robot swarms, considerations that were learned are presented.

Herein a method for object tracking and interception for applications in arm robotics is presented. Generality of five and six degree of freedom robots has traditionally been lost due to focus on pre-programmed dead-reckoning centric algorithms. The method presented herein utilizes high speed software engineering techniques in conjunction with image processing algorithms to produce a viable and extensible object tracking platform.

This paper explores autonomous navigation and obstacle avoidance techniques based on Q-learning for a mobile robot in a real environment. The implemented algorithm focuses on simplicity and efficiency. The learning process takes place in both simulation and real world allowing the combination of a longer learning time in the simulator with a more accurate knowledge from the real world. After learning is completed in simulation and in the real world, the robot was able to navigate without hitting obstacles and able to generate control law for complex situations such as corners and small objects.

This paper presents a system of systems approach to threat detection through integration of heterogeneous independently operable systems. The approach is presented on a realistic situation where a human-controlled base robot, swarm robot(s), and sensors work together to obtain a decision about a possible threat in the environment. The base robot is remotely operated by a human using a haptic control system. The swarm robot(s) are autonomous and can accept directives from the base robot. Finally, sensors directly communicate with (report to) the base robot. In this scenario, heterogeneous systems and human interact in a system of systems architecture. With the inclusion of human expert and sensor verification of swarm robots, the system can successfully perform the threat detection and reduce the false alarms. Finally, a system of systems simulation framework including a base robot, a swarm robot, and two sensors is presented in addition to an experimental evaluation of the proposed SoS architecture.

Mine detection is a sensitive task confronting the battlefield strategists. There is an ever-increasing demand for proper and sophisticated resources for many issues involved in the task. Traditional practices still involve human force directly in executing the tasks in spite of the advances in technology for tools and implements for the operation [GAO, 2001]. The problem includes various facets inherently: two of the prominent issues are location of mines over a minefield and secondly removal of the mines once located [GAO, 2001]. These two issues are not totally independent as technology used for one can directly or indirectly affect the other. Developments in artificial intelligence, natural heuristics, computational optimization and robotics have endowed us with the ability to realize unmanned robots (or robot like vehicles) that work intelligently on a real time basis in attempting at the problem of mine detection. In this paper we focus on the algorithms developed using ant colony optimization based approaches to the mine detection application and its implementation on a real-time basis. We focus on certain optimization techniques that could be used for effective realization of the algorithm. Generic groundscout robots had been already built at the MABL, RIT [Sahin F. et al., 2003]. These robots have been used to demonstrate the implementation

This paper presents architecture for a modular micro robotic platform for swarm intelligence and cooperative robotics research and applications. In a swarm the value of an individual is negligible since the goal of the swarm is essential. Thus, the agents (robots) need to be small, low cost, and cooperative. GroundScouts are designed based on these conditions. The proposed architecture slices a robot into abstract modules such as locomotion, control, sensors, communication, and actuation. Any mobile robot can be constructed by combining these abstract modules for a specific application. A modular embedded micro-OS with dynamic task uploading and multi-tasking abilities is developed. In order to create better interface between robots and the command center and among the robots. The dynamic, task uploading allows the robots change their behaviors in runtime. Thus, the robots can work in swarm, master-slave, or hybrid mode and possibly be used in other applications such as mobile sensor networks, remote sensing, and plant monitoring

This paper highlights the important points of swarm intelligence, more specifically the ant algorithm, and illustrate how it can be applied to a real time mine detection problem. The algorithm would be applied using GroundScouts, a modular micro robot that was designed for cooperative robotics applications. An adaptive time division multiple access (ATDMA) communication schemes are also presented that changes the behavior of the network according to the number of robots on the network. This maximizes the efficiency of the communication between the robots. The results show that the real time implementation of the algorithm is successful.

Multi-agent based solutions to problems, whether they are software agents or physical robots, are attractive because they are robust and scalable. Fundamental aspects of designing multi-agent systems involve modeling the intelligence of the agents and modeling their interactions. The intelligences of agents modeled here are encoded in Bayesian representations of their world. The agents interact only by observing others and moving in such a way so as to probabilistically maximize their internalized goal or utility. Using this multi-agent framework, a three agent herding is explored.

The field of robotics is in rapid development. As robots become cheaper to build, new applications involving many robots systems can be envisioned. One reason for using many robots is to achieve robustness. Having many robots, however, does not ensure robustness. A control strategy and robot behaviors must be engineered to incorporate robustness into the system. Swarm intelligence based approaches are popular for developing optimal and robust control strategies for systems of robots. Here we analyze the behavior of a swarm of robots modeled after a swarm of ants, where tasks are spatially distributed in the environment and robots/ants are recruited through short-range recruitment. For ants that move probabilistically in response to the short range signal and who adjust their probabilities such that they are near a phase change boundary, or edge-of-chaos, in the mean field analysis of their motions, we find a significant improvement in the robustness of the system.

A model for a Polyimide V-groove leg actuator with a Polysilicon type heater was simulated using ANSYS 5.6. Potential areas for improvement were identified. These include the relative expansion of the Polyimide within the V-groove during the heating cycle, and the heat conduction path during the Cooling cycle. Various geometries were investigated, and results were compared with a Plane Wall V-groove design. Significant Net Gain was observed for the case of uniform diaphragm thickness at the V-groove bottom. Considering the simplicity of fabrication of this case, the uniform diaphragm V-groove geometry appears worthy of further investigation.Copyright © 2003 by ASME

This paper presents a novel architecture for a mobile micro robot design. The architecture will have hardware and software modularity. The modular architecture of the platform provides “plug-and-play” capability that will allow hardware and software subsystems to be easily swapped. This paper focuses on vertical hardware modularity in the sense that modules will not be identical to each other but have common connectivity. Our approach slices a robot into functional modules such as locomotion, control, sensors, communication, and actuation. Any mobile robot can be constructed by combining the above abstract modules. A sub-module is a piece of hardware, which accomplishes the functionality of an abstract module, i.e. a wireless communication sub-module for a communication module. The software architecture consists of abstract classes and their objects. The abstract classes are “robot”, “locomotion”, “control”, “communication”, “sensor”, and “actuators”. From these abstract classes, concrete classes are derived. The objects are going to be created from the concrete classes. For example, “wireless” can be a class inherited from “communication” class. Then, an instance of “wireless” class can be created as the communication module in the robot. The objects (tasks) are dynamically loaded into the robots so that the modular OS can run the tasks on the sub-module it has. The paper explores generations of micro robot designs with modular architecture.Copyright © 2003 by ASME