Efficient Multi-agent Navigation with Lightweight DRL Policy

In this article, we present an end-to-end collision avoidance policy based on deep reinforcement learning (DRL) for multi-agent systems, demonstrating encouraging outcomes in real-world applications. In particular, our policy calculates the control commands of the agent based on the raw LiDAR observation. In addition, the number of parameters of the proposed basic model is 140,000, and the size of the parameter file is 3.5 MB, which allows the robot to calculate the actions from the CPU alone. We propose a multi-agent training platform based on a physics-based simulator to further bridge the gap between simulation and the real world. The policy is trained on a policy-gradients-based RL algorithm in a dense and messy training environment. A novel reward function is introduced to address the issue of agents choosing suboptimal actions in some common scenarios. Although the data used for training is exclusively from the simulation platform, the policy can be successfully transferred and deployed in real-world robots. Finally, our policy effectively responds to intentional obstructions and avoids collisions. The website is available at \url{https://sites.google.com/view/xingrong2024efficient/%E9%A6%96%E9%A1%B5}.

Graph Neural Network Based Method for Path Planning Problem

Sampling-based path planning is a widely used method in robotics, particularly in high-dimensional state space. Among the whole process of the path planning, collision detection is the most time-consuming operation. In this paper, we propose a learning-based path planning method that aims to reduce the number of collision detection. We develop an efficient neural network model based on Graph Neural Networks (GNN) and use the environment map as input. The model outputs weights for each neighbor based on the input and current vertex information, which are used to guide the planner in avoiding obstacles. We evaluate the proposed method's efficiency through simulated random worlds and real-world experiments, respectively. The results demonstrate that the proposed method significantly reduces the number of collision detection and improves the path planning speed in high-dimensional environments.