制約を考慮した拡散モデルによる軌道最適化
Constraint-Aware Diffusion Models for Trajectory Optimization
軌道最適化のための拡散モデルにおいて、制約違反を抑える新しいハイブリッド損失関数を導入し、卓上マニピュレーションと二車両の到達回避問題で従来法より優れることを示した。
著者: Anjian Li, Zihan Ding, Adji Bousso Dieng, Ryne Beeson
分類: cs.LG, cs.RO
原文アブストラクト
The diffusion model has shown success in generating high-quality and diverse solutions to trajectory optimization problems. However, diffusion models with neural networks inevitably make prediction errors, which leads to constraint violations such as unmet goals or collisions. This paper presents a novel constraint-aware diffusion model for trajectory optimization. We introduce a novel hybrid loss function for training that minimizes the constraint violation of diffusion samples compared to the groundtruth while recovering the original data distribution. Our model is demonstrated on tabletop manipulation and two-car reach-avoid problems, outperforming traditional diffusion models in minimizing constraint violations while generating samples close to locally optimal solutions.
