SwarmDiff: Swarm Robotic Trajectory Planning in Cluttered Environments via Diffusion Transformer

TL;DR

SwarmDiff introduces a hierarchical diffusion-based framework utilizing transformers and risk metrics to enhance trajectory planning in cluttered environments, improving efficiency, safety, and scalability for swarm robotics.

Contribution

The paper presents a novel hierarchical generative framework combining diffusion models, transformers, and risk metrics for scalable, safe, and efficient swarm robotic trajectory planning.

Findings

Outperforms existing methods in computational efficiency

Achieves higher trajectory validity and safety

Demonstrates scalability in complex environments

Abstract

Swarm robotic trajectory planning faces challenges in computational efficiency, scalability, and safety, particularly in complex, obstacle-dense environments. To address these issues, we propose SwarmDiff, a hierarchical and scalable generative framework for swarm robots. We model the swarm's macroscopic state using Probability Density Functions (PDFs) and leverage conditional diffusion models to generate risk-aware macroscopic trajectory distributions, which then guide the generation of individual robot trajectories at the microscopic level. To ensure a balance between the swarm's optimal transportation and risk awareness, we integrate Wasserstein metrics and Conditional Value at Risk (CVaR). Additionally, we introduce a Diffusion Transformer (DiT) to improve sampling efficiency and generation quality by capturing long-range dependencies. Extensive simulations and real-world experiments demonstrate that SwarmDiff outperforms existing methods in computational efficiency, trajectory validity, and scalability, making it a reliable solution for swarm robotic trajectory planning.