用扩散模型直接生成轨迹，零动态约束误差，无人机避障成功率提升4倍。
PAD-TRO: Projection-Augmented Diffusion for Direct Trajectory Optimization
- 直接生成状态序列，避免传统方法的迭代推演
- 引入无梯度投影机制，确保动力学可行性
- 适合需要高精度轨迹规划的无人机等系统
近年来，扩散模型因其建模多模态概率分布的能力，在轨迹优化中受到广泛关注。然而，如何处理非线性等式约束（即动力学可行性）仍是基于扩散模型的轨迹优化中的重大挑战。现有框架多采用单次射击法，将去噪后的控制序列用于前向传播动力系统，无法显式约束状态变量，常导致次优解。本文提出一种基于模型的直接轨迹优化新方法，直接生成状态序列。为确保动力学可行性，我们在逆扩散过程中引入无梯度投影机制。实验结果表明，与最新基线相比，本方法在包含密集静态障碍物的四旋翼航点导航任务中，实现零动力学可行性误差，并使成功率提升约4倍。
原文摘要 · Abstract (English)
Recently, diffusion models have gained popularity and attention in trajectory optimization due to their capability of modeling multi-modal probability distributions. However, addressing nonlinear equality constraints, i.e, dynamic feasibility, remains a great challenge in diffusion-based trajectory optimization. Recent diffusion-based trajectory optimization frameworks rely on a single-shooting style approach where the denoised control sequence is applied to forward propagate the dynamical system, which cannot explicitly enforce constraints on the states and frequently leads to sub-optimal solutions. In this work, we propose a novel direct trajectory optimization approach via model-based diffusion, which directly generates a sequence of states. To ensure dynamic feasibility, we propose a gradient-free projection mechanism that is incorporated into the reverse diffusion process. Our results show that, compared to a recent state-of-the-art baseline, our approach leads to zero dynamic feasibility error and approximately 4x higher success rate in a quadrotor waypoint navigation scenario involving dense static obstacles.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。