Reciprocal Velocity Obstacles for real-time multi-agent navigation

By Jur van den Berg, Ming C Lin, Dinesh Manocha. IEEE International Conference on Robotics and Automation, 2008

1,818 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Networks and Communications, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/3b22ce4c3243a0fc2ff68d91c7e1ae085f276452

How researchers see this paper

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

In Aerospace Engineering

In Computer Networks and Communications

In Computer Vision and Pattern Recognition

Citations in the corpus

Perception, Planning, Control, and Coordination for Autonomous Vehicles (2017, methodology): “This was generally applied to circular, holonomic robots, but due to the ease of computation it has gained popularity in multi-robot planning, with proposed Reciprocal Velocity Obstacles [237].”
Human motion trajectory prediction: a survey (2019, methodology): “To account for presence of other agents, several authors propose to modify individual optimal policies locally with physics-based methods (van Den Berg et al. 2008; Rudenko et al. 2018a; Wu et al. 2018).”
Graph Neural Networks for Decentralized Multi-Robot Path Planning (2019, methodology): “6: Histogram of proportion of cases distributed over the number of robots reaching their goal; the network with hop count K ∈ [2, 3], is trained on 10 robots and tested on 60 robots, with and without the OE.”
Optimal Multirobot Path Planning on Graphs: Complete Algorithms and Effective Heuristics (2015, methodology): “A representative method called velocity-obstacles Kant and Zucker (1986); van den Berg et al. (2008, 2011) explicitly examines velocity-time space for coordinating robot motions.”
Multi-vehicle Flocking Control with Deep Deterministic Policy Gradient Method (2018, methodology): “Based on the learned policy with designed reward function, the method is validated with improved performance to the ORCA method.”
Safety Barrier Certificates for Collisions-Free Multirobot Systems (2017, background): “, [23]–[25], whereby the robots no longer progress toward the realization of the primary objective.”
Learning for multi-robot cooperation in partially observable stochastic environments with macro-actions (2017, methodology): “Realtime multi-robot collision avoidance is conducted using the reciprocal velocity obstacles (RVO) formulation [29].”
Socially Compliant Navigation Through Raw Depth Inputs with Generative Adversarial Imitation Learning (2017, result): “It is similar to the concept of prefered velocity in other planning methods [18].”
Reciprocal n-Body Collision Avoidance (2011, methodology): “We believe that we can relatively easily replace the RVO formulation by our ORCA formulation in that implementation.”
Deep-Learned Collision Avoidance Policy for Distributed Multiagent Navigation (2016, methodology): “In this section, we provide a brief overview of prior work on collision avoidance for multi-agent navigation and machine learning for multi-agent systems.”
Crowd-Robot Interaction: Crowd-Aware Robot Navigation With Attention-Based Deep Reinforcement Learning (2018, methodology): “Methods Success Collision Time Reward ORCA [5] 0.”
Decentralized non-communicating multiagent collision avoidance with deep reinforcement learning (2016, methodology): “However, since reactionbased methods do not consider evolution of the neighboring agents’ future states, they are short-sighted in time and have been found to create oscillatory and unnatural behaviors in certain situations [10], [13].”
Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning (2018, background): “assumes other agents are dynamic obstacles, but with a constant velocity [1].”
Core Challenges of Social Robot Navigation: A Survey (2021, methodology): “Under the velocity-based modeling approaches, we can find techniques such as Velocity Obstacle (VO) [61], Reciprocal Velocity Obstacle (RVO) [240], Optimal Reciprocal Collision Avoidance (ORCA) [238], and Hybrid Reciprocal Velocity Obstacle (HRVO) [207].”
Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning (2017, background): “simulation based works [1], [6] assume that each agent has”
Optimal Reciprocal Collision Avoidance for Multiple Non-Holonomic Robots (2010, methodology): “Reciprocal Collision Avoidance (RVO) [3], a collaborative collision avoidance method based on velocity obstacles, was reformulated as ORCA [2] and shown to be solved efficiently through a low-dimensional linear program, which results in completeness and a speed-up of the algorithm.”