提出稳定轨迹优化的PISTO算法，提升成功率与速度。
PISTO: Proximal Inference for Stochastic Trajectory Optimization
- 引入近端推断机制，用KL正则约束连续更新
- 在机械臂任务中成功率达89%，路径更短更平滑
- 无需梯度信息，适合处理不连续成本函数
STOMP等随机轨迹优化方法可处理非可微代价函数，具有高度灵活性。我们发现STOMP隐式最小化了从Boltzmann轨迹分布出发的KL散度，揭示其背后存在优雅的变分推断结构。基于此，我们提出近端推断用于随机轨迹优化（PISTO）算法，通过在目标函数中加入连续高斯提议之间的KL正则项来稳定更新过程。该近端形式具有信赖域解释，并能以代理分布下的期望形式计算闭式均值更新。我们通过重要性加权蒙特卡洛采样估计这些期望，得到一种简单、无需导数的算法，保留了STOMP处理非可微和不连续代价的能力，无需修改。在机器人手臂运动规划基准测试中，PISTO达到89%的成功率——优于CHOMP（63%）和STOMP（68%），且路径更短更平滑，速度是现有随机方法的两倍。我们在接触丰富的MuJoCo运动与操作任务上进一步验证了PISTO，在奖励方面持续优于CEM和MPPI基线。
原文摘要 · Abstract (English)
Stochastic trajectory optimization methods like STOMP enable planning with non-differentiable costs, offering substantial flexibility over gradient-based approaches. We show that STOMP implicitly minimizes the KL divergence from a Boltzmann trajectory distribution, revealing an elegant Variational Inference (VI) structure underlying its updates. Building on this insight, we propose the \textit{Proximal Inference for Stochastic Trajectory Optimization} (PISTO) algorithm that stabilizes the updates by augmenting the objective with a KL regularization between successive Gaussian proposals. This proximal formulation admits a trust-region interpretation and yields closed-form mean updates computable as expectations under a surrogate distribution. We estimate these expectations via importance-weighted Monte Carlo sampling, producing a simple, derivative-free algorithm that inherits STOMP's ability to handle non-differentiable and discontinuous costs without modification. On robot arm motion planning benchmarks, PISTO achieves an 89\% success rate -- outperforming CHOMP (63\%) and STOMP (68\%) -- while producing shorter, smoother paths at twice the speed of competing stochastic methods. We further validate PISTO on contact-rich MuJoCo locomotion and manipulation tasks, where it consistently outperforms both CEM and MPPI baselines in reward.
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。