Search papers, labs, and topics across Lattice.
This paper introduces Model-Based Diffusion via Constraint Optimization and Adaptive Scheduling (MD-COAS) for Single-Robot Motion Planning (SRMP) in complex, constrained environments. By integrating an inexact Augmented Lagrangian Method (iALM) soft diffusion prior with a Convex Feasible Set (CFS)-based hard projection operator, MD-COAS adaptively schedules and co-optimizes safety enforcement alongside diffusion scheduling. Experimental results show that MD-COAS outperforms baseline planners, achieving higher safety and success rates, faster convergence, and lower final costs in challenging 2D benchmarks and a 7-DoF robot arm task.
Unifying soft and hard safety constraints in motion planning leads to significant improvements in safety and efficiency, outperforming traditional methods.
Single-Robot Motion Planning (SRMP) in highly non-convex constrained environments, where robots must satisfy collision-free guarantees, dynamic feasibility, and task-related constraints, is challenging under complex constraints and computational limits. Recent Model-Based Diffusion (MBD) approaches recast the SRMP as trajectory optimization that samples from a posterior over trajectories, using known dynamics, and analytically estimates the score function from rollout samples to guide diffusion denoising toward a low-cost, clean trajectory without demonstration learning. While existing works further adapt MBD to constrained environments and showcase promising performance, they are still limited by (1) enforcing safety either via soft feasibility diffusion priors or hard projection operators, but lack a unified framework to integrate both, and (2) fixing safety enforcement to neglect the changing of diffusion scheduling. Therefore, we introduce Model-Based Diffusion via Constraint Optimization and Adaptive Scheduling (MD-COAS) for SRMP that unifies the inexact Augmented Lagrangian Method (iALM) soft diffusion prior with a Convex Feasible Set (CFS)-based hard projection operator, and adaptively schedules and co-optimizes safety enforcement, along with diffusion scheduling. Experiments demonstrate that our method achieves higher safety \&success rates, faster convergence, and lower final costs than baseline planners on randomly generated highly non-convex 2D benchmarks and a 7-DoF robot arm avoidance task.
