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.

翻译：扩散模型在生成高质量、多样化的轨迹优化解方面已展现出成功应用。然而，基于神经网络的扩散模型不可避免地存在预测误差，这会导致约束违反，如目标未达成或发生碰撞。本文提出了一种用于轨迹优化的新型约束感知扩散模型。我们引入了一种新颖的混合损失函数进行训练，该函数在恢复原始数据分布的同时，最小化扩散样本相较于真实数据的约束违反程度。我们的模型在桌面操作和双车到达-避障问题上进行了验证，结果表明其在生成接近局部最优解样本的同时，在最小化约束违反方面优于传统扩散模型。