Bayesian Multi-Task Learning MPC for Robotic Mobile Manipulation

TL;DR

This paper introduces a Bayesian multi-task learning approach combined with model predictive control to improve robotic mobile manipulation by efficiently adapting to diverse tasks and uncertainties in real-time.

Contribution

It presents a novel Bayesian multi-task learning model using trigonometric basis functions for dynamic error identification, integrated with MPC for enhanced robotic manipulation.

Findings

Improved control performance over baseline controllers.

Effective online adaptation to new tasks.

Successful simulation and hardware experiments.

Abstract

Mobile manipulation in robotics is challenging due to the need of solving many diverse tasks, such as opening a door or picking-and-placing an object. Typically, a basic first-principles system description of the robot is available, thus motivating the use of model-based controllers. However, the robot dynamics and its interaction with an object are affected by uncertainty, limiting the controller's performance. To tackle this problem, we propose a Bayesian multi-task learning model that uses trigonometric basis functions to identify the error in the dynamics. In this way, data from different but related tasks can be leveraged to provide a descriptive error model that can be efficiently updated online for new, unseen tasks. We combine this learning scheme with a model predictive controller, and extensively test the effectiveness of the proposed approach, including comparisons with available baseline controllers. We present simulation tests with a ball-balancing robot, and door-opening hardware experiments with a quadrupedal manipulator.