面向任务的残差动力学主动学习用于模型预测路径积分控制
Task-Oriented Active Learning of Residual Dynamics for Model Predictive Path Integral Control
查看机构详情
- Technical University of Munich（慕尼黑工业大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本文提出任务导向信息获取（ToIA）准则，用于MPPI控制中的在线GP残差学习，通过加权任务相关性选择信息，在模拟越野导航中显著提升成功率。
中文摘要 AI 辅助
在线残差学习可以减少预测控制中的模型失配，但被动数据收集可能无法充分覆盖在任务后期变得重要的状态。任务无关的主动学习针对不确定或信息丰富的区域，但在这些区域获取的信息不一定能提高任务性能。本文提出了任务导向信息获取（ToIA），一种用于模型预测路径积分控制（MPPI）与在线高斯过程（GP）残差学习的主动学习准则。对于每个采样的控制序列，ToIA估计在滚动过程中早期获得的观测将如何减少同一滚动后期状态下的预测不确定性，并根据该滚动与任务的相关性对该减少量进行加权。该分数在现有的MPPI滚动批次上评估，无需采样未来观测或在假设的后验更新下重新优化控制。在具有异质地形的保留地图上的模拟越野导航中，与被动GP学习相比，ToIA将目标到达成功率提高了19.3和27.4个百分点，并在密集和稀疏在线学习间隔中优于任务无关的主动学习基线。消融研究表明，在稀疏模型更新下，任务相关性尤为重要。该实现支持在NVIDIA RTX 2080 Ti上以20 Hz进行在线控制。
英文摘要
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.
