Task-Oriented Active Learning of Residual Dynamics for Model Predictive Path Integral Control

2026-09-16

AI Summary

本文提出了一种任务导向的信息获取方法（ToIA），通过在线高斯过程残差学习来减少预测控制中的模型不匹配问题，从而提高路径积分控制的任务性能。

Abstract

Online residual learning can reduce model mismatch in predictive control, but passive data collection may fail to adequately cover states that become important later in the task. Task-agnostic active learning targets uncertain or informative regions, but information acquired in such regions does not necessarily improve task performance. This paper introduces Task-Oriented Information Acquisition (ToIA), an active-learning criterion for model predictive path integral control (MPPI) with online Gaussian process (GP) residual learning. For each sampled control sequence, ToIA estimates how much an observation obtained early in the rollout would reduce predictive uncertainty at later states on the same rollout, and weights this reduction by the rollout's relevance to the task. The score is evaluated over the existing MPPI rollout batch without sampling future observations or re-optimizing control under hypothetical posterior updates. In simulated off-road navigation across held-out maps with heterogeneous terrain, ToIA improved the goal-reaching success rate over passive GP learning by 19.3 and 27.4 percentage points and outperformed task-agnostic active-learning baselines across dense and sparse online-learning intervals. An ablation study indicates that task relevance is particularly important under sparse model updates. The implementation supports online control at 20 Hz on an NVIDIA RTX 2080 Ti.

Problem

• online residual learning
• model predictive path integral control
• active learning
• task performance
• predictive uncertainty

Innovation

• Task-Oriented Information Acquisition
• Model Predictive Path Integral Control
• Online Gaussian Process
• Residual Learning
• Active Learning