Showing papers on "Obstacle avoidance published in 2020"

A Review of Motion Planning for Highway Autonomous Driving

Abstract: Self-driving vehicles will soon be a reality, as main automotive companies have announced that they will sell their driving automation modes in the 2020s. This technology raises relevant controversies, especially with recent deadly accidents. Nevertheless, autonomous vehicles are still popular and attractive thanks to the improvement they represent to people’s way of life (safer and quicker transit, more accessible, comfortable, convenient, efficient, and environment-friendly). This paper presents a review of motion planning techniques over the last decade with a focus on highway planning. In the context of this article, motion planning denotes path generation and decision making. Highway situations limit the problem to high speed and small curvature roads, with specific driver rules, under a constrained environment framework. Lane change, obstacle avoidance, car following, and merging are the situations addressed in this paper. After a brief introduction to the context of autonomous ground vehicles, the detailed conditions for motion planning are described. The main algorithms in motion planning, their features, and their applications to highway driving are reviewed, along with current and future challenges and open issues.

A Motion Planning and Tracking Framework for Autonomous Vehicles Based on Artificial Potential Field Elaborated Resistance Network Approach

Abstract: This paper presents a novel motion planning and tracking framework for automated vehicles based on artificial potential field (APF) elaborated resistance approach. Motion planning is one of the key parts of autonomous driving, which plans a sequence of movement states to help vehicles drive safely, comfortably, economically, human-like, etc. In this paper, the APF method is used to assign different potential functions to different obstacles and road boundaries; while the drivable area is meshed and assigned resistance values in each edge based on the potential functions. A local current comparison method is employed to find a collision-free path. As opposed to a path, the vehicle motion or trajectory should be planned spatiotemporally. Therefore, the entire planning process is divided into two spaces, namely the virtual and actual. In the virtual space, the vehicle trajectory is predicted and executed step by step over a short horizon with the current vehicle speed. Then, the predicted trajectory is evaluated to decide if the speed should be kept or changed. Finally, it will be sent to the actual space, where an experimentally validated Carsim model controlled by a model predictive controller is used to track the planned trajectory. Several case studies are presented to demonstrate the effectiveness of the proposed framework.

Obstacle Avoidance and Tracking Control of Redundant Robotic Manipulator: An RNN-Based Metaheuristic Approach

Abstract: In this article, we present a metaheuristic-based control framework, called beetle antennae olfactory recurrent neural network, for simultaneous tracking control and obstacle avoidance of a redundant manipulator. The ability to avoid obstacles while tracking a predefined reference path is critical for any industrial manipulator. The formulated control framework unifies the tracking control and obstacle avoidance into a single constrained optimization problem by introducing a penalty term into the objective function, which actively rewards the optimizer for avoiding the obstacles. One of the significant features of the proposed framework is the way that the penalty term is formulated following a straightforward principle: maximize the minimum distance between a manipulator and an obstacle. The distance calculations are based on Gilbert–Johnson–Keerthi algorithm, which calculates the distance between a manipulator and an obstacle by directly using their three-dimensional geometries, which also implies that our algorithm works for a manipulator and an arbitrarily shaped obstacle. Theoretical treatment proves the stability and convergence, and simulations results using an LBR IIWA seven-DOF manipulator are presented to analyze the performance of the proposed framework.

Dynamic obstacle avoidance for quadrotors with event cameras

Abstract: Today’s autonomous drones have reaction times of tens of milliseconds, which is not enough for navigating fast in complex dynamic environments. To safely avoid fast moving objects, drones need low-latency sensors and algorithms. We departed from state-of-the-art approaches by using event cameras, which are bioinspired sensors with reaction times of microseconds. Our approach exploits the temporal information contained in the event stream to distinguish between static and dynamic objects and leverages a fast strategy to generate the motor commands necessary to avoid the approaching obstacles. Standard vision algorithms cannot be applied to event cameras because the output of these sensors is not images but a stream of asynchronous events that encode per-pixel intensity changes. Our resulting algorithm has an overall latency of only 3.5 milliseconds, which is sufficient for reliable detection and avoidance of fast-moving obstacles. We demonstrate the effectiveness of our approach on an autonomous quadrotor using only onboard sensing and computation. Our drone was capable of avoiding multiple obstacles of different sizes and shapes, at relative speeds up to 10 meters/second, both indoors and outdoors.

Improved Artificial Potential Field Method Applied for AUV Path Planning

Abstract: With the topics related to the intelligent AUV, control and navigation have become one of the key researching fields. This paper presents a concise and reliable path planning method for AUV based on the improved APF method. AUV can make the decision on obstacle avoidance in terms of the state of itself and the motion of obstacles. The artificial potential field (APF) method has been widely applied in static real-time path planning. In this study, we present the improved APF method to solve some inherent shortcomings, such as the local minima and the inaccessibility of the target. A distance correction factor is added to the repulsive potential field function to solve the GNRON problem. The regular hexagon-guided method is proposed to improve the local minima problem. Meanwhile, the relative velocity method about the moving objects detection and avoidance is proposed for the dynamic environment. This method considers not only the spatial location but also the magnitude and direction of the velocity of the moving objects, which can avoid dynamic obstacles in time. So the proposed path planning method is suitable for both static and dynamic environments. The virtual environment has been built, and the emulation has been in progress in MATLAB. Simulation results show that the proposed method has promising feasibility and efficiency in the AUV real-time path planning. We demonstrate the performance of the proposed method in the real environment. Experimental results show that the proposed method is capable of avoiding the obstacles efficiently and finding an optimized path.

Image-Based Visual Servoing of Helical Microswimmers for Planar Path Following

Abstract: Magnetically actuated microswimmers have attracted researchers to investigate their swimming characteristics and controlled actuation. Although plenty of studies on actuating helical microswimmers have been carried out, robust closed-loop controls should be still explored for practical applications. In this paper, we proposed a data-driven model-free method using Image-Based Visual Servoing (IBVS), which uses features directly extracted in the image space as feedbacks. The IBVS method can eliminate camera calibration errors. We have demonstrated with experiments that the proposed IBVS method can enable velocity-independent path following of an arbitrarily given path on the plane, which permits a better experience of user interaction. The proposed control method is successfully applied to obstacle avoidance tasks and has the potential for the application in complex circumstances. This approach is promising for biomedical applications. Note to Practitioners —This paper is motivated by the problem of driving a small-scale swimming robot with a helical body by magnetic fields along a predefined path. The proposed new closed-loop control uses features directly extracted in the image space as feedbacks. We demonstrated with experiments that the helical swimming robot can follow an arbitrarily given path on the plane using the proposed control method. The proposed control method is also successfully applied to obstacle avoidance tasks.

Safety-Critical Model Predictive Control with Discrete-Time Control Barrier Function

Abstract: The optimal performance of robotic systems is usually achieved near the limit of state and input bounds. Model predictive control (MPC) is a prevalent strategy to handle these operational constraints, however, safety still remains an open challenge for MPC as it needs to guarantee that the system stays within an invariant set. In order to obtain safe optimal performance in the context of set invariance, we present a safety-critical model predictive control strategy utilizing discrete-time control barrier functions (CBFs), which guarantees system safety and accomplishes optimal performance via model predictive control. We analyze the stability and the feasibility properties of our control design. We verify the properties of our method on a 2D double integrator model for obstacle avoidance. We also validate the algorithm numerically using a competitive car racing example, where the ego car is able to overtake other racing cars.

Path planning for intelligent robots based on deep Q-learning with experience replay and heuristic knowledge

Abstract: Path planning and obstacle avoidance are two challenging problems in the study of intelligent robots. In this paper, we develop a new method to alleviate these problems based on deep Q-learning with experience replay and heuristic knowledge. In this method, a neural network has been used to resolve the “ curse of dimensionality ” issue of the Q-table in reinforcement learning. When a robot is walking in an unknown environment, it collects experience data which is used for training a neural network ; such a process is called experience replay. Heuristic knowledge helps the robot avoid blind exploration and provides more effective data for training the neural network. The simulation results show that in comparison with the existing methods, our method can converge to an optimal action strategy with less time and can explore a path in an unknown environment with fewer steps and larger average reward.

Hybrid Path Planning Based on Safe A* Algorithm and Adaptive Window Approach for Mobile Robot in Large-Scale Dynamic Environment

Abstract: When mobile robot used in large-scale dynamic environments, it face more challenging problems in real-time path planning and collision-free path tracking. This paper presents a new hybrid path planning method that combines A* algorithm with adaptive window approach to conduct global path planning, real-time tracking and obstacles avoidance for mobile robot in large-scale dynamic environments. Firstly, a safe A* algorithm is designed to simplify the calculation of risk cost function and distance cost. Secondly, key path points are extracted from the planned path which generated by the safe A* to reduce the number of the grid nodes for smooth path tracking. Finally, the real-time motion planning based on adaptive window approach is adopted to achieve the simultaneous path tracking and obstacle avoidance (SPTaOA) together the switching of the key path points. The simulation and practical experiments are conducted to verify the feasibility and performance of the proposed method. The results show that the proposed hybrid path planning method, used for global path planning, tracking and obstacles avoidance, can meet the application needs of mobile robots in complex dynamic environments.

Path Planning for UAV Ground Target Tracking via Deep Reinforcement Learning

Abstract: In this paper, we focus on the study of UAV ground target tracking under obstacle environments using deep reinforcement learning, and an improved deep deterministic policy gradient (DDPG) algorithm is presented . A reward function based on line of sight and artificial potential field is constructed to guide the behavior of UAV to achieve target tracking , and a penalty term of action makes the trajectory smooth . In order to improve the exploration ability, multiple UAVs, which controlled by the same policy network, are used to perform tasks in each episode. Taking into account that the history observations have a great degree of correlation with the policy, long short-term memory networks are used to approximate the state of environments, which improve the approximation accuracy and the efficiency of data utilization. The simulation results show that the propose method can make the UAV keep target tracking and obstacle avoidance effectively .

Recovery RL: Safe Reinforcement Learning with Learned Recovery Zones

Abstract: Safety remains a central obstacle preventing widespread use of RL in the real world: learning new tasks in uncertain environments requires extensive exploration, but safety requires limiting exploration. We propose Recovery RL, an algorithm which navigates this tradeoff by (1) leveraging offline data to learn about constraint violating zones before policy learning and (2) separating the goals of improving task performance and constraint satisfaction across two policies: a task policy that only optimizes the task reward and a recovery policy that guides the agent to safety when constraint violation is likely. We evaluate Recovery RL on 6 simulation domains, including two contact-rich manipulation tasks and an image-based navigation task, and an image-based obstacle avoidance task on a physical robot. We compare Recovery RL to 5 prior safe RL methods which jointly optimize for task performance and safety via constrained optimization or reward shaping and find that Recovery RL outperforms the next best prior method across all domains. Results suggest that Recovery RL trades off constraint violations and task successes 2 - 20 times more efficiently in simulation domains and 3 times more efficiently in physical experiments. See this https URL for videos and supplementary material.

Vision Aided Dynamic Exploration of Unstructured Terrain with a Small-Scale Quadruped Robot

Abstract: Legged robots have been highlighted as promising mobile platforms for disaster response and rescue scenarios because of their rough terrain locomotion capability. In cluttered environments, small robots are desirable as they can maneuver through small gaps, narrow paths, or tunnels. However small robots have their own set of difficulties such as limited space for sensors, limited obstacle clearance, and scaled-down walking speed. In this paper, we extensively address these difficulties via effective sensor integration and exploitation of dynamic locomotion and jumping. We integrate two Intel RealSense sensors into the MIT Mini-Cheetah, a 0.3 m tall, 9 kg quadruped robot. Simple and effective filtering and evaluation algorithms are used for foothold adjustment and obstacle avoidance. We showcase the exploration of highly irregular terrain using dynamic trotting and jumping with the small-scale, fully sensorized Mini-Cheetah quadruped robot.

Long-Range Indoor Navigation With PRM-RL

Abstract: Long-range indoor navigation requires guiding robots with noisy sensors and controls through cluttered environments along paths that span a variety of buildings. We achieve this with PRM-RL, a hierarchical robot navigation method in which reinforcement learning (RL) agents that map noisy sensors to robot controls learn to solve short-range obstacle avoidance tasks, and then sampling-based planners map where these agents can reliably navigate in simulation; these roadmaps and agents are then deployed on robots, guiding them along the shortest path where the agents are likely to succeed. In this article, we use probabilistic roadmaps (PRMs) as the sampling-based planner, and AutoRL as the RL method in the indoor navigation context. We evaluate the method with a simulation for kinematic differential drive and kinodynamic car-like robots in several environments, and on differential-drive robots at three physical sites. Our results show that PRM-RL with AutoRL is more successful than several baselines, is robust to noise, and can guide robots over hundreds of meters in the face of noise and obstacles in both simulation and on robots, including over 5.8 km of physical robot navigation.

Human-like driving behaviour emerges from a risk-based driver model.

Abstract: Current driving behaviour models are designed for specific scenarios, such as curve driving, obstacle avoidance, car-following, or overtaking. However, humans can drive in diverse scenarios. Can we find an underlying principle from which driving behaviour in different scenarios emerges? We propose the Driver’s Risk Field (DRF), a two-dimensional field that represents the driver’s belief about the probability of an event occurring. The DRF, when multiplied with the consequence of the event, provides an estimate of the driver’s perceived risk. Through human-in-the-loop and computer simulations, we show that human-like driving behaviour emerges when the DRF is coupled to a controller that maintains the perceived risk below a threshold-level. The DRF model predictions concur with driving behaviour reported in literature for seven different scenarios (curve radii, lane widths, obstacle avoidance, roadside furniture, car-following, overtaking, oncoming traffic). We conclude that our generalizable DRF model is scientifically satisfying and has applications in automated vehicles.

The autonomous navigation and obstacle avoidance for USVs with ANOA deep reinforcement learning method

Abstract: The unmanned surface vehicle (USV) has been widely used to accomplish missions in the sea or dangerous marine areas for ships with sailors, which greatly expands protective capability and detection range. When USVs perform various missions in sophisticated marine environment, autonomous navigation and obstacle avoidance will be necessary and essential. However, there are few effective navigation methods with real-time path planning and obstacle avoidance in dynamic environment. With tailored design of state and action spaces and a dueling deep Q-network, a deep reinforcement learning method ANOA (Autonomous Navigation and Obstacle Avoidance) is proposed for the autonomous navigation and obstacle avoidance of USVs. Experimental results demonstrate that ANOA outperforms deep Q-network (DQN) and Deep Sarsa in the efficiency of exploration and the speed of convergence not only in static environment but also in dynamic environment. Furthermore, the ANOA is integrated with the real control model of a USV moving in surge, sway and yaw and it achieves a higher success rate than Recast navigation method in dynamic environment.

Active SLAM for Mobile Robots With Area Coverage and Obstacle Avoidance

Abstract: In this article, we present an active simultaneous localization and mapping (SLAM) framework for a mobile robot to obtain a collision-free trajectory with good performance in SLAM uncertainty reduction and in an area coverage task. Based on a model predictive control framework, these two tasks are solved by the introduction of a control switching mechanism. For SLAM uncertainty reduction, graph topology is used to approximate the original problem as a constrained nonlinear least squares problem. A convex half-space representation is applied to relax nonconvex spatial constraints that represent obstacle avoidance. Using convex relaxation, the problem is solved by a convex optimization method and a rounding procedure based on singular value decomposition. The area coverage task is addressed with a sequential quadratic programming method. A submap joining approach, called linear SLAM, is used to address the associated challenges of avoiding local minima, minimizing control switching, and potentially high computational cost. Finally, various simulations and experiments using an aerial robot are presented that verify the effectiveness of the proposed method, showing that our method produces a more accurate SLAM result and is more computationally efficient compared with multiple existing methods.

Nonlinear MPC for Collision Avoidance and Control of UAVs With Dynamic Obstacles

Abstract: This article proposes a Novel Nonlinear Model Predictive Control (NMPC) for navigation and obstacle avoidance of an Unmanned Aerial Vehicle (UAV). The proposed NMPC formulation allows for a fully p ...

Integrated Perception and Control at High Speed: Evaluating Collision Avoidance Maneuvers Without Maps

Abstract: We present a method for robust high-speed quadrotor flight through unknown cluttered environments using integrated perception and control. Motivated by experiments in which the difficulty of accurate state estimation was a primary limitation on speed, our method forgoes maintaining a map in favor of using only instantaneous depth information in the local frame. This provides robustness in the presence of significant state estimate uncertainty. Additionally, we present approximation methods augmented with spatial partitioning data structures that enable low-latency, real-time reactive control. The probabilistic formulation provides a natural way to integrate reactive obstacle avoidance with arbitrary navigation objectives. We validate the method using a simulated quadrotor race through a forest at high speeds in the presence of increasing state estimate noise. We pair our method with a motion primitive library and compare with a global path-generation and pathfollowing approach.

Ant-Colony-Based Complete-Coverage Path-Planning Algorithm for Underwater Gliders in Ocean Areas With Thermoclines

Abstract: Underwater gliders are being increasingly used for data collection, and the development of methods for optimizing their routes has become a topic of active research. With this aim in mind, in this paper, a complete-coverage path-planning obstacle-avoidance (CCPP-OA) algorithm that ensures avoidance for underwater gliders in sea areas with thermoclines is proposed. First, the entire sea area with the thermocline layer is stratified based on the underwater communication radii of the gliders. Next, the glide angles and initial navigation points of the gliders are determined based on their communication radii at each level to construct the complete-coverage path. Finally, by combining the ant colony algorithm and the determined initial navigation points, the complete-coverage path with obstacle avoidance is planned for the gliders. Simulation results show that the proposed CCPP-OA algorithm enables complete coverage of the entire sea area. Furthermore, the length of the planned path is shorter and the amount of energy consumed is less than that of other algorithms.

An AI-Based Visual Aid With Integrated Reading Assistant for the Completely Blind

Abstract: Blindness prevents a person from gaining knowledge of the surrounding environment and makes unassisted navigation, object recognition, obstacle avoidance, and reading tasks a major challenge. In this work, we propose a novel visual aid system for the completely blind. Because of its low cost, compact size, and ease-of-integration, Raspberry Pi 3 Model B+ has been used to demonstrate the functionality of the proposed prototype. The design incorporates a camera and sensors for obstacle avoidance and advanced image processing algorithms for object detection. The distance between the user and the obstacle is measured by the camera as well as ultrasonic sensors. The system includes an integrated reading assistant, in the form of the image-to-text converter, followed by an auditory feedback. The entire setup is lightweight and portable and can be mounted onto a regular pair of eyeglasses, without any additional cost and complexity. Experiments are carried out with 60 completely blind individuals to evaluate the performance of the proposed device with respect to the traditional white cane. The evaluations are performed in controlled environments that mimic real-world scenarios encountered by a blind person. Results show that the proposed device, as compared with the white cane, enables greater accessibility, comfort, and ease of navigation for the visually impaired.

EVDodgeNet: Deep Dynamic Obstacle Dodging with Event Cameras

Abstract: Dynamic obstacle avoidance on quadrotors requires low latency. A class of sensors that are particularly suitable for such scenarios are event cameras. In this paper, we present a deep learning based solution for dodging multiple dynamic obstacles on a quadrotor with a single event camera and on-board computation. Our approach uses a series of shallow neural networks for estimating both the ego-motion and the motion of independently moving objects. The networks are trained in simulation and directly transfer to the real world without any fine-tuning or retraining. We successfully evaluate and demonstrate the proposed approach in many real-world experiments with obstacles of different shapes and sizes, achieving an overall success rate of 70% including objects of unknown shape and a low light testing scenario. To our knowledge, this is the first deep learning – based solution to the problem of dynamic obstacle avoidance using event cameras on a quadrotor. Finally, we also extend our work to the pursuit task by merely reversing the control policy, proving that our navigation stack can cater to different scenarios.

Distributed Leader–Follower Affine Formation Maneuver Control for High-Order Multiagent Systems

Abstract: To steer a group of agents to maneuver with the desired collective forms, this article studies the affine formation maneuver control of high-order multiagent systems using a two-layered leader-follower strategy, in which agents are divided into three types: first leader, second leader group, and followers. The first leader will decide the whole formation's maneuver parameters, and the second leader group will keep the desired relative positions with respect to the first leader. The followers aim at moving to the desired positions affinely localized by the leaders. The main feature of this two-layered leader-follower strategy is that the information interaction from the first leader to the second leader group can be realized via wireless communication, and only the measurements of local relative position and its finite-order time-derivatives are needed for the followers. To achieve the control objective under the given constraints, the distributed control algorithms are designed for the second leader group and followers, in which the backstepping, distributed estimation, $PD^m$ , and adaptive gain design techniques are employed. Finally, a simulation example with obstacle avoidance is provided to validate the effectiveness of the proposed control algorithms.

Autonomous navigation and obstacle avoidance of an omnidirectional mobile robot using swarm optimization and sensors deployment

Abstract: The present work deals with the design of intelligent path planning algorithms for a mobile robot in static and dynamic environments based on swarm intelligence optimization. Two modifications are ...