D4orm: Multi-Robot Trajectories with Dynamics-aware Diffusion Denoised Deformations

This work presents an optimization method for generating kinodynamically feasible and collision-free multi-robot trajectories that exploits an incremental denoising scheme in diffusion models. Our key insight is that high-quality trajectories can be discovered merely by denoising noisy trajectories sampled from a distribution. This approach has no learning component, relying instead on only two ingredients: a dynamical model of the robots to obtain feasible trajectories via rollout, and a fitness function to guide denoising with Monte Carlo gradient approximation. The proposed framework iteratively optimizes a deformation for the previous trajectory with the current denoising process, allows anytime refinement as time permits, supports different dynamics, and benefits from GPU acceleration. Our evaluations for differential-drive and holonomic teams with up to 16 robots in 2D and 3D worlds show its ability to discover high-quality solutions faster than other black-box optimization methods such as MPPI. In a 2D holonomic case with 16 robots, it is almost twice as fast. As evidence for feasibility, we demonstrate zero-shot deployment of the planned trajectories on eight multirotors.

Authors

• Yuhao Zhang
• Keisuke Okumura 0001
• Heedo Woo
• Ajay Shankar
• Amanda Prorok

Keywords

• Three-dimensional displays
• Monte Carlo methods
• Deformation
• Noise reduction
• Optimization methods
• Graphics processing units
• Diffusion models
• Trajectory
• Noise measurement
• Intelligent robots
• Dynamical
• Optimization Method
• Fitness Function
• Diffusion Model
• Iterative Optimization
• Robot Model
• Evidence For The Feasibility
• Black-box Optimization
• Collision-free Trajectory
• Quantitative Evaluation
• Feasible Solution
• Image Generation
• Path Planning
• Previous Iteration
• Solution Quality
• Reward Function
• Numerical Optimization
• Target Distribution
• Trajectory Optimization
• Candidate Solutions
• Sampling-based Methods
• Trajectory Control
• Joint Trajectories
• Joint Representation
• Robot Dynamics
• Planning Horizon