Learning to Schedule in Multi-Agent Pathfinding

In this work, we consider the problem of allocating tasks and planning paths for multiple robots to operate cooper-atively. We formulate the problem as a bi-level optimization that involves optimizing the scheduling of robots and the collision-free path for each robot. To address the complexity of the environment with obstacles, we introduce a congestion-aware state representation technique with the aid of graph neural networks. We also derive a joint scheduling policy using multi-agent reinforcement learning, and we propose an additional auxiliary loss that promotes coordination among the robots. Through empirical evaluation, we demonstrate the effectiveness of our approach in solving the combined task allocation and path planning problem in a cooperative multi-robot system.

Authors

• Kyuree Ahn
• Heemang Park
• Jinkyoo Park

Keywords

• Schedules
• Robot kinematics
• Reinforcement learning
• Path planning
• Resource management
• Multi-robot systems
• Task analysis
• Multi-Agent Path Finding
• Neural Network
• Multi-agent Systems
• Graph Neural Networks
• Task Allocation
• Bilevel Optimization
• Multiple Robots
• Auxiliary Loss
• Multi-agent Reinforcement Learning
• Robot Path
• Collision-free Path
• Optimization Algorithm
• Optimal Combination
• Manhattan Distance
• Sequential Task
• Node Features
• Policy Network
• Edge Features
• Policy Gradient
• Node Embeddings
• Task Scheduling
• Bilevel Problem
• Makespan
• Node Update
• Agency Costs
• High-level Policy
• Joint Policy
• Cost Path
• Joint Task