外观
论文arXiv 2609.283251 个月前
用于模型预测路径积分控制的运动神经元启发式采样
原文链接：Motoneuron-Inspired Sampling for Model Predictive Path Integral Control（arXiv 2609.28325 · 发布日期：2026-09-23）
Motoneuron-Inspired Sampling for Model Predictive Path Integral Control
针对 MPPI 有限 rollout 下采样分布影响性能的问题，提出运动神经元启发的 Spike-MPPI，并在 MuJoCo Ant 模型上验证。
核心要点
- 问题/动机：MPPI 依赖随机轨迹采样，有限 rollout 预算下对提议分布结构很敏感。
- 方法：Spike-MPPI 用简化运动神经元动力学生成时间结构化控制扰动。
- 实验与结果：在两类 MuJoCo Ant 作动模型中，相比高斯采样提升执行控制平滑性。
- 结果分析：任务性能影响取决于 rollout 条件和作动方式，谱匹配可复现大量行为。
验证范围与局限：验证范围为通用 MPPI 框架中的扭矩作动与拮抗作动 MuJoCo Ant 模型。
英文摘要 (Abstract)
Model Predictive Path Integral (MPPI) control relies on stochastic trajectory sampling, and its performance under limited rollout budgets depends strongly on the structure of the proposal distribution. Standard implementations commonly perturb control sequences with Gaussian noise, despite growing evidence that temporally correlated and structured sampling can improve finite-budget control. We introduce Spike-MPPI, a motoneuron-inspired proposal that generates temporally structured perturbations through a simplified model of motoneuron dynamics. The proposal is evaluated within a common MPPI framework on torque-actuated and antagonistically actuated MuJoCo Ant models against standard Gaussian sampling and spectrum-matched Gaussian controls. Results show that structured sampling substantially improves executed-control smoothness, while its effect on task performance depends on rollout condition and robot actuation. Spectrum matching reproduces a substantial part of the observed behavior, while the full Spike proposal retains additional effects beyond second-order spectral structure. These results support treating proposal design as a combination of second-order spectral structure and higher-order statistical organization.
作者：Alexis Poignant, Jan Babič
来源
本页事实对应的公开页面，以原文为准。