运动神经元启发的模型预测路径积分控制采样
Motoneuron-Inspired Sampling for Model Predictive Path Integral Control
浏览论文内容
中文总结 AI 辅助
本文提出运动神经元启发的Spike-MPPI采样方法，通过结构化扰动提升MPPI控制平滑度，并揭示频谱结构与高阶统计的作用。
中文摘要 AI 辅助
模型预测路径积分（MPPI）控制依赖于随机轨迹采样，在有限的滚动预算下，其性能在很大程度上取决于提议分布的结构。标准实现通常使用高斯噪声扰动控制序列，尽管越来越多的证据表明，时间相关和结构化的采样可以改善有限预算下的控制。我们提出了Spike-MPPI，一种受运动神经元启发的提议，通过运动神经元动力学的简化模型生成时间结构化的扰动。该提议在一个通用的MPPI框架中，在力矩驱动和拮抗驱动的MuJoCo Ant模型上，与标准高斯采样和频谱匹配的高斯控制进行了评估。结果表明，结构化采样显著提高了执行控制的平滑度，而其任务性能的影响取决于滚动条件和机器人驱动方式。频谱匹配再现了所观察行为的大部分，而完整的Spike提议保留了超出二阶频谱结构的额外效应。这些结果支持将提议设计视为二阶频谱结构和更高阶统计组织的组合。
英文摘要
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.
