Multi-agent navigation based on deep reinforcement learning and traditional pathfinding algorithm

2020/12/05 by Hongda Qiu, Qiu, Hongda
Computer Science · Engineering · #Autonomous Vehicle Technology and Safety #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multiagent Systems (cs.MA) #Reinforcement Learning in Robotics #Robotic Path Planning Algorithms #Robotics (cs.RO) #cs.LG #cs.MA #cs.RO

paper · pdf · doi:10.48550/arxiv.2012.09134

arxiv created 2020/12/05 · openalex publication_date 2020/12/05 · arxiv updated 2020/12/17 · openalex created_date 2020/12/21 · openalex updated_date 2026/07/28

Abstract

We develop a new framework for multi-agent collision avoidance problem. The framework combined traditional pathfinding algorithm and reinforcement learning. In our approach, the agents learn whether to be navigated or to take simple actions to avoid their partners via a deep neural network trained by reinforcement learning at each time step. This framework makes it possible for agents to arrive terminal points in abstract new scenarios. In our experiments, we use Unity3D and Tensorflow to build the model and environment for our scenarios. We analyze the results and modify the parameters to approach a well-behaved strategy for our agents. Our strategy could be attached in different environments under different cases, especially when the scale is large.

Citations

• Self-organized formation of topologically correct feature maps
• Conflict-based search for optimal multi-agent pathfinding
• Guided Deep Reinforcement Learning for Swarm Systems
• Towards Optimally Decentralized Multi-Robot Collision Avoidance via Deep Reinforcement Learning
• MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments

Related

• Decentralized Non-communicating Multiagent Collision Avoidance with Deep Reinforcement Learning
• Hierarchical Reinforcement Learning Framework towards Multi-agent Navigation
• Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning
• Robot Navigation with Entity-Based Collision Avoidance using Deep Reinforcement Learning
• Reciprocal Collision Avoidance for General Nonlinear Agents using Reinforcement Learning