Optimal Reciprocal Collision Avoidance for Multiple Non-Holonomic Robots

By Javier Alonso-Mora, Andreas Breitenmoser, Martin Rufli, Paul A. Beardsley, Roland Yves Siegwart. International Symposium on Distributed Autonomous Robotic Systems, 2010

322 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Computer Vision and Pattern Recognition, Control and Systems Engineering

View Paper: https://www.semanticscholar.org/paper/fa79ed5545130252ee9d1e1580bfa859f468ed5c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

A Survey and Analysis of Multi-Robot Coordination (2013, unknown): “A high-level coordination concept combined with reactive control for robots should be more efficient [169] [170].”
Safety Barrier Certificates for Collisions-Free Multirobot Systems (2017, methodology): “A similar idea was pursued in [10], [11], where a so-called “velocity obstacle” method was used to calculate the optimal, safe velocity.”
Predicting actions to act predictably: Cooperative partial motion planning with maximum entropy models (2016, background): “This interestingly establishes a link to former motion planning techniques such as the dynamic window approach [20], where multiobjective optimization criteria are encoded in the same fashion.”
Trajectory Planning for Quadrotor Swarms (2018, background): “Collisionavoidance approaches [13], [14] let each robot plan its trajectory independently and resolve conflicts in real time when impending collisions are detected.”
Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning (2017, methodology): “2) Circle scenarios: We first compare our multi-scenario multi-stage learned policy with the NH-ORCA policy [19], and the policy trained using supervised learning (SL-policy, a variation of [10], see below for details) on circle scenarios with different number of robots.”
Learning a Decentralized Multi-arm Motion Planner (2020, background): “Non-Holonomic Optimal Reciprocal Collision Avoidance (NH-ORCA) [30] is a popular approach for distributed multi-robot planning and collision avoidance, but is sensitive to hyper-parameters.”
Perception, Planning, Control, and Coordination for Autonomous Vehicles (2017, unknown): “Recent extensions to the velocity obstacles method have further incorporated acceleration constraints [238], and adjustments for nonholonomic robots [239].”