Collision avoidance

About: Collision avoidance is a research topic. Over the lifetime, 8014 publications have been published within this topic receiving 111414 citations.

ClearPath: highly parallel collision avoidance for multi-agent simulation

Abstract: We present a new local collision avoidance algorithm between multiple agents for real-time simulations. Our approach extends the notion of velocity obstacles from robotics and formulates the conditions for collision free navigation as a quadratic optimization problem. We use a discrete optimization method to efficiently compute the motion of each agent. This resulting algorithm can be parallelized by exploiting data-parallelism and thread-level parallelism. The overall approach, ClearPath, is general and can robustly handle dense scenarios with tens or hundreds of thousands of heterogeneous agents in a few milli-seconds. As compared to prior collision avoidance algorithms, we observe more than an order of magnitude performance improvement.

Cooperative UAV Formation Flying With Obstacle/Collision Avoidance

Abstract: Navigation problems of unmanned air vehicles (UAVs) flying in a formation in a free and an obstacle-laden environment are investigated in this brief. When static obstacles popup during the flight, the UAVs are required to steer around them and also avoid collisions between each other. In order to achieve these goals, a new dual-mode control strategy is proposed: a "safe mode" is defined as an operation in an obstacle-free environment and a "danger mode" is activated when there is a chance of collision or when there are obstacles in the path. Safe mode achieves global optimization because the dynamics of all the UAVs participating in the formation are taken into account in the controller formulation. In the danger mode, a novel algorithm using a modified Grossberg neural network (GNN) is proposed for obstacle/collision avoidance. This decentralized algorithm in 2-D uses the geometry of the flight space to generate optimal/suboptimal trajectories. Extension of the proposed scheme for obstacle avoidance in a 3-D environment is shown. In order to handle practical vehicle constraints, a model predictive control-based tracking controller is used to track the references generated. Numerical results are provided to motivate this approach and to demonstrate its potential.

Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning

Abstract: Finding feasible, collision-free paths for multiagent systems can be challenging, particularly in non-communicating scenarios where each agent's intent (e.g. goal) is unobservable to the others. In particular, finding time efficient paths often requires anticipating interaction with neighboring agents, the process of which can be computationally prohibitive. This work presents a decentralized multiagent collision avoidance algorithm based on a novel application of deep reinforcement learning, which effectively offloads the online computation (for predicting interaction patterns) to an offline learning procedure. Specifically, the proposed approach develops a value network that encodes the estimated time to the goal given an agent's joint configuration (positions and velocities) with its neighbors. Use of the value network not only admits efficient (i.e., real-time implementable) queries for finding a collision-free velocity vector, but also considers the uncertainty in the other agents' motion. Simulation results show more than 26% improvement in paths quality (i.e., time to reach the goal) when compared with optimal reciprocal collision avoidance (ORCA), a state-of-the-art collision avoidance strategy.

Effective Coverage Control for Mobile Sensor Networks With Guaranteed Collision Avoidance

Abstract: This paper studies the problem of dynamically covering a given region in the plane using a set of mobile sensor agents. A novel problem formulation is proposed that addresses a number of important multiagent missions. The coverage goal, which is to cover a given search domain using multiple mobile sensors such that each point is surveyed until a certain preset level is achieved, is formulated in a mathematically precise problem statement. A control law is developed that guarantees to meet the coverage goal. This control law is modified to guarantee that a partially connected fleet also attains the coverage goal. Finally, a collision avoidance component is added to the controller to guarantee that the agents do not collide. The new controller is shown to safely achieve coverage. Several numerical examples are provided to illustrate the main results.

Safe Maritime Autonomous Navigation With COLREGS, Using Velocity Obstacles

Abstract: This paper presents an autonomous motion planning algorithm for unmanned surface vehicles (USVs) to navigate safely in dynamic, cluttered environments. The algorithm not only addresses hazard avoidance (HA) for stationary and moving hazards, but also applies the International Regulations for Preventing Collisions at Sea (known as COLREGS, for COLlision REGulationS). The COLREGS rules specify, for example, which vessel is responsible for giving way to the other and to which side of the “stand-on” vessel to maneuver. Three primary COLREGS rules are considered in this paper: crossing, overtaking, and head-on situations. For autonomous USVs to be safely deployed in environments with other traffic boats, it is imperative that the USV's navigation algorithm obeys COLREGS. Furthermore, when other boats disregard their responsibility under COLREGS, the USV must fall back to its HA algorithms to prevent a collision. The proposed approach is based on velocity obstacles (VO) method, which generates a cone-shaped obstacle in the velocity space. Because VOs also specify on which side of the obstacle the vehicle will pass during the avoidance maneuver, COLREGS are encoded in the velocity space in a natural way. Results from several experiments involving up to four vessels are presented, in what we believe is the first on-water demonstration of autonomous COLREGS maneuvers without explicit intervehicle communication. We also show an application of this motion planner to a target trailing task, where a strategic planner commands USV waypoints based on high-level objectives, and the local motion planner ensures hazard avoidance and compliance with COLREGS during a traverse.