MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments

07/30/2020
by   Zuxin Liu, et al.
0

Multi-agent navigation in dynamic environments is of great industrial value when deploying a large scale fleet of robot to real-world applications. This paper proposes a decentralized partially observable multi-agent path planning with evolutionary reinforcement learning (MAPPER) method to learn an effective local planning policy in mixed dynamic environments. Reinforcement learning-based methods usually suffer performance degradation on long-horizon tasks with goal-conditioned sparse rewards, so we decompose the long-range navigation task into many easier sub-tasks under the guidance of a global planner, which increases agents' performance in large environments. Moreover, most existing multi-agent planning approaches assume either perfect information of the surrounding environment or homogeneity of nearby dynamic agents, which may not hold in practice. Our approach models dynamic obstacles' behavior with an image-based representation and trains a policy in mixed dynamic environments without homogeneity assumption. To ensure multi-agent training stability and performance, we propose an evolutionary training approach that can be easily scaled to large and complex environments. Experiments show that MAPPER is able to achieve higher success rates and more stable performance when exposed to a large number of non-cooperative dynamic obstacles compared with traditional reaction-based planner LRA* and the state-of-the-art learning-based method.

READ FULL TEXT
research
10/02/2021

AB-Mapper: Attention and BicNet Based Multi-agent Path Finding for Dynamic Crowded Environment

Multi-agent path finding in dynamic crowded environments is of great aca...
research
09/19/2023

Crowd-Aware Multi-Agent Pathfinding With Boosted Curriculum Reinforcement Learning

Multi-Agent Path Finding (MAPF) in crowded environments presents a chall...
research
02/08/2022

Multi-Agent Path Finding with Prioritized Communication Learning

Multi-agent pathfinding (MAPF) has been widely used to solve large-scale...
research
03/21/2022

Long Short-Term Memory for Spatial Encoding in Multi-Agent Path Planning

Reinforcement learning-based path planning for multi-agent systems of va...
research
06/21/2021

Distributed Heuristic Multi-Agent Path Finding with Communication

Multi-Agent Path Finding (MAPF) is essential to large-scale robotic syst...
research
02/25/2021

Where to go next: Learning a Subgoal Recommendation Policy for Navigation Among Pedestrians

Robotic navigation in environments shared with other robots or humans re...
research
03/09/2023

Intent-based Deep Reinforcement Learning for Multi-agent Informative Path Planning

In multi-agent informative path planning (MAIPP), agents must collective...

Please sign up or login with your details

Forgot password? Click here to reset