通过低通滤波提升模型预测路径积分控制的效率与平滑性
LP-MPPI: Low-Pass Filtering for Efficient Model Predictive Path Integral Control
- 在采样过程中引入低通滤波，抑制高频噪声扰动
- 在多个环境测试中性能优于现有MPPI变体，减少控制抖动
- 适合需要平稳控制信号的机器人实时系统应用
模型预测路径积分（MPPI）控制是一种广泛使用的基于采样的实时控制方法，因其在处理任意动力学和代价函数时的灵活性而备受青睐。然而，其采样控制轨迹常受高频噪声影响，阻碍最优控制搜索并传递至实际控制，导致执行器磨损。本文提出低通滤波模型预测路径积分控制（LP-MPPI），将低通滤波集成到采样过程中，消除有害的高频成分，提升算法效率。与以往方法不同，LP-MPPI可直接、可解释地控制采样控制轨迹扰动的频谱特性，实现更高效的采样与更平滑的控制。在Gymnasium环境、模拟四足行走及真实F1TENTH自动驾驶赛车中的大量实验表明，LP-MPPI始终优于最先进的MPPI变体，在显著提升性能的同时降低控制信号抖动。
原文摘要 · Abstract (English)
Model Predictive Path Integral (MPPI) control is a widely used sampling-based approach for real-time control, valued for its flexibility in handling arbitrary dynamics and cost functions. However, it often suffers from high-frequency noise in the sampled control trajectories, which hinders the search for optimal controls and transfers to the applied controls, leading to actuator wear. In this work, we introduce Low-Pass Model Predictive Path Integral Control (LP-MPPI), which integrates low-pass filtering into the sampling process to eliminate detrimental high-frequency components and enhance the algorithm's efficiency. Unlike prior approaches, LP-MPPI provides direct and interpretable control over the frequency spectrum of sampled control trajectory perturbations, leading to more efficient sampling and smoother control. Through extensive evaluations in Gymnasium environments, simulated quadruped locomotion, and real-world F1TENTH autonomous racing, we demonstrate that LP-MPPI consistently outperforms state-of-the-art MPPI variants, achieving significant performance improvements while reducing control signal chattering.
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。