Agile Mobility with Rapid Online Adaptation via Meta-learning and Uncertainty-aware MPPI

TL;DR

This paper introduces a meta-learning based control approach that enables rapid online adaptation of mobile robot controllers to changing dynamics and uncertainties, reducing the need for extensive tuning.

Contribution

The work presents a full model-learning controller using meta pre-training that adapts quickly with few-shot data and accounts for model uncertainty across different robots and scenarios.

Findings

Comparable to domain-specific controllers in performance

Effective in simulation and real hardware tests

Generalizes well across diverse settings

Abstract

Modern non-linear model-based controllers require an accurate physics model and model parameters to be able to control mobile robots at their limits. Also, due to surface slipping at high speeds, the friction parameters may continually change (like tire degradation in autonomous racing), and the controller may need to adapt rapidly. Many works derive a task-specific robot model with a parameter adaptation scheme that works well for the task but requires a lot of effort and tuning for each platform and task. In this work, we design a full model-learning-based controller based on meta pre-training that can very quickly adapt using few-shot dynamics data to any wheel-based robot with any model parameters, while also reasoning about model uncertainty. We demonstrate our results in small-scale numeric simulation, the large-scale Unity simulator, and on a medium-scale hardware platform with a wide range of settings. We show that our results are comparable to domain-specific well-engineered controllers, and have excellent generalization performance across all scenarios.