Search

Semantic simultaneous localization and mapping (SLAM) is susceptible to several sources of noise that hinder the accuracy of its trajectory and map estimates. Such sources include inaccurate landmark pose estimation and sensor limitations. In this paper, a novel deep learning based approach is proposed to improve the accuracy of semantic SLAM by reducing the trajectory estimation error. A deep neural network consisting of various non-linear activation functions is structured and pre-trained by means of an unsupervised greedy layer-wise pre-training technique. The network is then fine-tuned using the adaptive moment estimation (Adam) optimizer. The training datasets were collected using several simulated and realtime experiments and are composed of two parts, the estimated trajectory and the corresponding ground truth. Ground truth trajectories were obtained using a motion capture system in realtime experiments. The effectiveness of the proposed approach was shown through simulated experiments, real-time experiments, and a sequence from the Technical University of Munich (TUM) RGB-D dataset. The performance of the deep neural network (DNN) was tested with different pre-training techniques and the proposed unsupervised greedy layer-wise pre-training technique proved to perform the best across training, validation, and testing datasets in terms of reducing the mean absolute trajectory error (ATE).

In this paper, we introduce a coverage path planning algorithm with adaptive viewpoint sampling to construct accurate 3D models of complex large structures using Unmanned Aerial Vehicle (UAV). The developed algorithm, Adaptive Search Space Coverage Path Planner (ASSCPP), utilizes an existing 3D reference model of the complex structure and the onboard sensors' noise models to generate paths that are evaluated based on the traveling distance and the quality of the model. The algorithm generates a set of viewpoints by performing adaptive sampling that directs the search towards areas with low accuracy and low coverage. The algorithm predicts the coverage percentage obtained by following the generated coverage path using the reference model. A set of experiments were conducted in real and simulated environments with structures of different complexities to test the validity of the proposed algorithm.

Edge devices often have to processdata at low power and would benefit from being adaptable. Given that the data coming into these devices is generally unlabeled, unsupervised training on these devices is beneficial. This paper examines a low power approach to implement the winner takes all algorithm, for self-organizing maps through a memristor crossbar based circuit. A novel neuron circuit is designed for the winning neuron detection and lateral inhibition operations. Our experimental results show that the proposed system can self-organize based on unlabeled training data. The proposed design was around 0.002mm$^{\mathbf{2\, $textbf{{in area and consumed about 0.2mW of power. When compared to a CPU, the design had a higher error rate, but was 100 times faster and consumed much lower area and power. Thus when area or power reduction are crucially important, this approach is quite viable.

Custom low power hardware for network intrusion detection is in great demand, as this would allow for efficient security in battery-powered network devices. This paper presents a memristor crossbar based Multilayer Perceptron (MLP) capable of performing network intrusion detection. The MLP is trained based on the Knowledge Discovery and Datamining (KDD) dataset. Once the network is trained, the weight values are programmed into a simulated memristor crossbar hardware system to show that custom circuitry can be designed to perform on-chip intrusion detection. We show the proposed memristor system is capable of achieving greater than 99% intrusion detection accuracy if the memristors utilized are able to store at least 4 unique values (essentially acting as 2-bit devices). Furthermore, we present a number of studies that quantify the amount of classification accuracy lost due to analog processing and amplification in the signal path. This circuit is capable of tolerating significant amplifier gain error (up to 30%) before classification accuracy drops below 99%.

Nowadays, multi-rotor Unmanned Aerial Vehicles (UAVs) are deployed widely in different fields to serve multiple purposes. Safety and reliability of multi-rotor system are rapidly growing research area, and enhancing the control design to account for system failure. In this paper, the Fault-Tolerance Control (FTC) is introduced as a method for recovery from failure in quad-rotor UAV actuator in hovering mode. The ultimate aim is to land safely with minimal damage. This research focuses on designing a FTC method that is capable of handling one and/or two rotors failures. Two different controllers are designed and implemented in simulation for controlling the UAV which are Proportional-Integral-Derivative (PID) control and Linear Quadratic Regulator (LQR). LQR shows its effectiveness after comparing both methods responses. Furthermore, a state observer is designed using Linear Quadratic Estimator (LQE). Gain scheduling (GS) method is developed to switch between the controllers of the system in the event of failure. The GS-PID control design is validated in ROS/Gazebo using the new Robotics System Toolbox showing the effectiveness of the proposed method.

In this paper we introduce a novel rewarding scheme for the classical POMDP formulation. The proposed scheme aims to reinforce preference of objectives. It ensures that a high-priority preferences get high accumulative rewards, solve ambiguities and it can be conducted before the low-priority-preference. In order to show conflicting of objectives, context of search and rescue has been selected for this paper. It involves heterogeneous team with potential conflicting multiobjective situations. Our rewarding scheme has been tested in simulated scenarios using multiple POMDP solvers. Results obtained from the simulated experiments show that the system is able to represent an impact on the human (first responder) through enforcing priority of objectives and iteratively optimize policies to better suit the first responder and the search and rescue mission goals.

In this paper, we introduce a coverage path planning algorithm for inspecting large structures optimized to generate highly accurate 3D models. Robotic inspection of structures such as aircrafts, bridges and buildings, is considered a critical task since missing any detail could affect the performance and integrity of the structures. Additionally, it is a time and resource intensive task that should be performed as efficiently and accurately as possible. The method we propose is a model based coverage path planning approach that generates an optimized path that passes through a set of admissible waypoints to cover a complex structure. The coverage path planning algorithm is developed with a heuristic reward function that exploits our knowledge of the structure mesh model, and the UAV's onboard sensors' models to generate optimal paths that maximizes coverage and accuracy, and minimizes distance travelled. Moreover, we accelerated critical components of the algorithm utilizing the Graphics Processing Unit (GPU) parallel architecture. A set of experiments were conducted in a simulated environment to test the validity of the proposed algorithm.

Motivated by the need to regulate and regularly inspect construction sites, we developed a real-time robust drone system that performs site inspection and violation detection in construction sites. The proposed system uses the drone to inspect and monitor numerous types of construction sites remotely from any control station or a nearby locations. Our drone system was developed as an entry to participate in “Drones For Good” 2015 competition, and qualified to the finals. Our proposed technological solution presented in this paper introduces the possible utilization of drone technology in the construction industry. We will first introduce the motivation and benefits of using this system, and how it's usage will increase the ability to control the health and safety, efficiency, and cost of the site inspection process. We will then detail the technical components of the drone, and present the results of experiments and evaluations conducted in realistic scenarios.

This paper presents a framework for modelling the interaction between a human operator and a robotic device, that enables the robot to collaborate with the human to jointly accomplish tasks. States of the system are captured in a model based on a partially observable Markov decision process (POMDP). States representing the human operator are motivated by behaviours from the psychology of the human action cycle. Hierarchical nature of these states allows the exploitation of data structures based on algebraic decision diagrams (ADD) to efficiently solve the resulting POMDP. The proposed framework is illustrated using two examples from as-sistive robotics; a robotic wheel chair and an intelligent walking device. Experimental results from trials conducted in an office environment with the wheelchair is used to demonstrate the proposed technique. © 2011 IEEE.

This paper presents an intelligent decision-making agent to assist wheelchair users in their daily navigation activities. Several navigational techniques have been successfully developed in the past to assist with specific behaviours such as "door passing" or "corridor following". These shared control strategies normally require the user to manually select the level of assistance required during use. Recent research has seen a move towards more intelligent systems that focus on forecasting users' intentions based on current and past actions. However, these predictions have been typically limited to locations immediately surrounding the wheelchair. The key contribution of the work presented here is the ability to predict the users' intended destination at a larger scale, that of a typical office arena. The systems relies on minimal user input - obtained from a standard wheelchair joystick - in conjunction with a learned Partially Observable Markov Decision Process (POMDP), to estimate and subsequently drive the user to his destination. The projection is constantly being updated, allowing for true user-platform integration. This shifts users' focus from fine motor-skilled control to coarse control broadly intended to convey intention. Successful simulation and experimental results on a real wheelchair robot demonstrate the validity of the approach. ©2008 IEEE.

Electric wheelchairs give otherwise immobile people the free-dom of movement, they significantly increase independence and dramatically increase quality of life. However the physical control systems of such wheelchair can be prohibitive for some users; for example, people with severe tremors. Several assisted wheelchair platforms have been developed in the past to assist such users. Algorithms that assist specific behaviors such as door - passing, follow - corridor, or avoid - obstacles have been successful. Recent research has seen a move towards systems that predict the users intentions, based on the users input. These predictions have been typically limited to locations immediately surrounding the wheelchair. This paper presents a new assisted wheelchair driving system with large scale intelligent intention recognition based on POMDPs (Partially Observable Markov Decision Processes). The systems acts as an intelligent agent/decision-maker, it relies on minimal user input; to predict the users intention and then autonomously drives the user to his destination. The prediction is constantly being updated as new user input is received allowing for true user/system integration. This shifts the users focus from fine motor-skilled control to coarse control intended to convey intention. © 2007 IEEE.

This paper presents a one step smooth and efficient path planning algorithm for navigating a large robotic platform in known cluttered environments. The proposed strategy, based on the generation of a novel search space, relies on non-uniform density sampling of the free areas to direct the computational resources to troubled and difficult regions, such as narrow passages, leaving the larger open spaces sparsely populated. A smoothing penalty is also associated to the nodes to encourage the generation of gentle paths along the middle of the empty spaces. Collision detection is carried out off-line during the creation of the configuration space to speed up the actual search for the path, which is done on-line. Results prove that the proposed approach considerably reduces the search space in a meaningful and practical manner, improving the computational cost of generating a path optimised for fine and smooth motion. © 2006 IEEE.