Implicit Coordination in Crowded Multi-Agent Navigation

In crowded multi-agent navigation environments, the motion of the agents is significantly constrained by the motion of the nearby agents. This makes planning paths very difficult and leads to inefficient global motion. To address this problem, we propose a new distributed approach to coordinate the motions of agents in crowded environments. With our approach, agents take into account the velocities and goals of their neighbors and optimize their motion accordingly and in real-time. We experimentally validate our coordination approach in a variety of scenarios and show that its performance scales to scenarios with hundreds of agents.

• Publication year

  2016

• Venue

  AAAI Conference on Artificial Intelligence

• Publication date

  2016-02-12

• Fields of study

  Computer Science

• Identifiers
  DOI 10.1609/aaai.v30i1.10131
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Artificial Intelligence

  2017cited by this paper
• Multi-Agent Path Finding with Kinematic Constraints

  2016cited by this paper
• Prioritized group navigation with Formation Velocity Obstacles

  2015cited by this paper
• Feasibility Study: Using Highways for Bounded-Suboptimal Multi-Agent Path Finding

  2015cited by this paper
• Adaptive Learning for Multi-Agent Navigation

  2015influential reference
• Robot navigation in dense human crowds: Statistical models and experimental studies of human–robot cooperation

  2015cited by this paper
• MARL-Ped: A multi-agent reinforcement learning based framework to simulate pedestrian groups

  2014cited by this paper
• Real-time navigation in crowded dynamic environments using Gaussian process motion control

  2014cited by this paper
• Autonomous agents and multi-agent systems

  2014cited by this paper
• Simulating and Evaluating the Local Behavior of Small Pedestrian Groups

  2012cited by this paper
• Interactive simulation of dynamic crowd behaviors using general adaptation syndrome theory

  2012cited by this paper
• Trends in cognitive sciences

  2012cited by this paper
• Mitochondrial dysfunction - the beginning of the end in Alzheimer's disease? Separate and synergistic modes of tau and amyloid-β toxicity

  2011cited by this paper
• Reciprocal n-Body Collision Avoidance

  2011cited by this paper
• Directing Crowd Simulations Using Navigation Fields

  2011cited by this paper
• Decentralized MDPs with sparse interactions

  2011cited by this paper
• How simple rules determine pedestrian behavior and crowd disasters

  2011cited by this paper
• Virtual Tawaf: A case study in simulating the behavior of dense, heterogeneous crowds

  2011cited by this paper
• graphics

  2011cited by this paper
• Modeling pedestrian crowd behavior based on a cognitive model of social comparison theory

  2010cited by this paper
• A synthetic-vision based steering approach for crowd simulation

  2010cited by this paper
• Crowd Simulation Via Multi-Agent Reinforcement Learning

  2010cited by this paper
• ClearPath: highly parallel collision avoidance for multi-agent simulation

  2009cited by this paper
• Aggregate dynamics for dense crowd simulation

  2009cited by this paper
• Coordinating Agent Plans Through Distributed Constraint Optimization

  2008cited by this paper
• Direction Maps for Cooperative Pathfinding

  2008cited by this paper
• Continuum crowds

  2006cited by this paper
• Autonomous pedestrians

  2005cited by this paper
• An asynchronous complete method for distributed constraint optimization

  2003cited by this paper
• An Asynchronous Complete Method for General Distributed Constraint Optimization

  2002cited by this paper
• Context-specific multiagent coordination and planning with factored MDPs

  2002cited by this paper
• Computational and mathematical organization theory

  2001cited by this paper
• Motion Planning in Dynamic Environments Using Velocity Obstacles

  1998cited by this paper
• Social force model for pedestrian dynamics.

  1995cited by this paper
• Flocks, herds, and schools: a distributed behavioral model

  1987cited by this paper
• Eurographics/ Acm Siggraph Symposium on Computer Animation (2007) Controlling Individual Agents in High-density Crowd Simulation

  year unknowncited by this paper

• Internal State Estimation in Crowds via Active Information Gathering

  2025cites this paper
• Learning System-Optimal and Individual-Optimal Collision Avoidance Behaviors by Autonomous Mobile Agents

  2025cites this paper
• Internal State Estimation in Groups via Active Information Gathering

  2025cites this paper
• Deep Reinforcement Learning With Multiple Unrelated Rewards for AGV Mapless Navigation

  2025cites this paper
• When, What, and with Whom to Communicate: Enhancing RL-based Multi-Robot Navigation through Selective Communication

  2024cites this paper
• Reinforcement Learning Algorithms For Navigating Multiagent In Auto Storage System

  2024cites this paper
• A literature review of dense crowd simulation

  2024cites this paper
• Towards Efficient Distributed Collision Avoidance for Heterogeneous Mobile Robots

  2024cites this paper
• Multi-robot collision avoidance method in sweet potato fields

  2024cites this paper
• Counterfactual Fairness Filter for Fair-Delay Multi-Robot Navigation

  2023cites this paper
• Differentiable Learning of Scalable Multi-Agent Navigation Policies

  2023cites this paper
• Vision-based Distributed Multi-UAV Collision Avoidance via Deep Reinforcement Learning for Navigation

  2022cites this paper
• Semi-autonomous Planning: A novel approach for plan segmentation in multiagent planning

  2022cites this paper
• Active-sensing-based decentralized control of autonomous mobile agents for quick and smooth collision avoidance

  2022cites this paper
• Anticipating Collisions, Navigating in Complex Environments, Elbowing, Pushing, and Smartphone-Walking: A Versatile Agent-Based Model for Pedestrian Dynamics

  2022cites this paper
• Toward Task Capable Active Matter: Learning to Avoid Clogging in Confined Collectives via Collisions

  2022cites this paper
• Body and mind: Decoding the dynamics of pedestrians and the effect of smartphone distraction by coupling mechanical and decisional processes

  2022cites this paper
• Human motion modeling and data generation tool for tracking algorithms development

  2022cites this paper
• Scalable multirobot planning for informed spatial sampling

  2021cites this paper
• A fully distributed multi-robot navigation method without pre-allocating target positions

  2021cites this paper
• Scalable Multi-Robot System for Non-myopic Spatial Sampling

  2021cites this paper
• Directionality Reinforcement Learning to Operate Multi-Agent System without Communication

  2021cites this paper
• Decentralised control of multiple mobile agents for quick, smooth, and safe movement

  2021cites this paper
• Navigation in Large Groups of Robots

  2020cites this paper
• Reward Value-Based Goal Selection for Agents’ Cooperative Route Learning Without Communication in Reward and Goal Dynamism

  2020cites this paper
• Distributed multi-robot collision avoidance via deep reinforcement learning for navigation in complex scenarios

  2020influential citation
• Simulating multi‐exit evacuation using deep reinforcement learning

  2020cites this paper
• Distributed Non-Communicating Multi-Robot Collision Avoidance via Map-Based Deep Reinforcement Learning

  2020cites this paper
• Cooperative Multi-Robot Navigation in Dynamic Environment with Deep Reinforcement Learning

  2020cites this paper
• C-Nav: Distributed coordination in crowded multi-agent navigation

  2020cites this paper
• Towards Autonomous Intralogistics: A Testbed Environment for the Coordination of a Robotic Fleet

  2020cites this paper
• LAC-Nav: Collision-Free Mutiagent Navigation Based on The Local Action Cells

  2019cites this paper
• Coordinating Multi-Agent Navigation by Learning Communication

  2019cites this paper
• Cumulative Training and Transfer Learning for Multi-Robots Collision-Free Navigation Problems

  2019cites this paper
• Taking Less Detour when Avoiding the Collisions

  2018cites this paper
• Efficient Reciprocal Collision Avoidance between Heterogeneous Agents Using CTMAT

  2018cites this paper
• Multi-Robot Cooperative Navigation

  2018cites this paper
• Structured Kernel Subspace Learning for Autonomous Robot Navigation †

  2018cites this paper
• Fully Distributed Multi-Robot Collision Avoidance via Deep Reinforcement Learning for Safe and Efficient Navigation in Complex Scenarios

  2018cites this paper
• Emergent behaviors and scalability for multi-agent reinforcement learning-based pedestrian models

  2017cites this paper
• Deep-learned Pedestrian Avoidance for Robot Navigation Interim Report

  2017cites this paper
• Deep-learned Pedestrian Avoidance for Robot Navigation Final Report

  2017cites this paper
• Deep-learned Pedestrian Avoidance for Robot Navigation Final Report

  2017cites this paper
• Quantifying and Detecting Collective Motion by Manifold Learning

  2017cites this paper
• Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning

  2017cites this paper
• Forecast the Plausible Paths in Crowd Scenes

  2017cites this paper
• Deep-Learned Collision Avoidance Policy for Distributed Multiagent Navigation

  2016cites this paper
• Dynamic group behaviors for interactive crowd simulation

  2016cites this paper
• Action Selection Methods for Multi-Agent Navigation in Crowded Environments

  2016cites this paper
• Moving in a Crowd: Safe and Efficient Navigation among Heterogeneous Agents

  2016cites this paper