Multi-Agent Formation Navigation Using Diffusion-Based Trajectory Generation

TL;DR

This paper presents a diffusion-based trajectory planner for multi-agent formation control in cluttered environments, enabling smooth and reliable leader-follower formations with low tracking errors.

Contribution

It introduces a novel diffusion-based planning method that generates trajectories for multi-agent formations, improving smoothness and reliability over traditional approaches.

Findings

Produces smooth trajectories with low tracking errors.

Effective in cluttered environments with complex obstacle configurations.

Most failures occur only in narrow or unseen obstacle spaces.

Abstract

This paper introduces a diffusion-based planner for leader--follower formation control in cluttered environments. The diffusion policy is used to generate the trajectory of the midpoint of two leaders as a rigid bar in the plane, thereby defining their desired motion paths in a planar formation. While the followers track the leaders and form desired foramtion geometry using a distance-constrained formation controller based only on the relative positions in followers' local coordinates. The proposed approach produces smooth motions and low tracking errors, with most failures occurring in narrow obstacle-free space, or obstacle configurations that are not in the training data set. Simulation results demonstrate the potential of diffusion models for reliable multi-agent formation planning.