Search papers, labs, and topics across Lattice.
This paper introduces a diffusion model-based multi-robot path planner that can generalize to scenarios with more robots than seen during training. The key innovation is a shared diffusion model coupled with inter-agent attention and temporal convolutions, enabling effective planning even with a significantly larger number of agents at deployment. Experiments demonstrate the method's ability to outperform multi-agent RL and heuristic approaches in scenarios with dynamically varying numbers of agents.
Scale your multi-robot planning without retraining: a diffusion model trained on a small team can effectively orchestrate much larger robot swarms.
Learning based multi-robot path planning methods struggle to scale or generalize to changes, particularly variations in the number of robots during deployment. Most existing methods are trained on a fixed number of robots and may tolerate a reduced number during testing, but typically fail when the number increases. Additionally, training such methods for a larger number of agents can be both time consuming and computationally expensive. However, analytical methods can struggle to scale computationally or handle dynamic changes in the environment. In this work, we propose to leverage a diffusion model based planner capable of handling dynamically varying number of agents. Our approach is trained on a limited number of agents and generalizes effectively to larger numbers of agents during deployment. Results show that integrating a single shared diffusion model based planner with dedicated inter-agent attention computation and temporal convolution enables a train small deploy-large paradigm with good accuracy. We validate our method across multiple scenarios and compare the performance with existing multi-agent reinforcement learning techniques and heuristic control based methods.
