Context-Aware Deep Lagrangian Networks for Model Predictive Control

TL;DR

This paper introduces a context-aware extension of Deep Lagrangian Networks combined with online system identification and model predictive control to adaptively manage complex, uncertain environments in robotic manipulation.

Contribution

It presents a novel integration of context-aware DeLaN with recurrent networks and MPC, enabling adaptive, physics-consistent control in dynamic environments.

Findings

Reduces end-effector tracking error by 39% in experiments.

Outperforms baseline methods like extended Kalman filter by significant margin.

Demonstrates effective online adaptation in a 7-DOF robot arm.

Abstract

Controlling a robot based on physics-consistent dynamic models, such as Deep Lagrangian Networks (DeLaN), can improve the generalizability and interpretability of the resulting behavior. However, in complex environments, the number of objects to potentially interact with is vast, and their physical properties are often uncertain. This complexity makes it infeasible to employ a single global model. Therefore, we need to resort to online system identification of context-aware models that capture only the currently relevant aspects of the environment. While physical principles such as the conservation of energy may not hold across varying contexts, ensuring physical plausibility for any individual context-aware model can still be highly desirable, particularly when using it for receding horizon control methods such as model predictive control (MPC). Hence, in this work, we extend DeLaN to make it context-aware, combine it with a recurrent network for online system identification, and integrate it with an MPC for adaptive, physics-consistent control. We also combine DeLaN with a residual dynamics model to leverage the fact that a nominal model of the robot is typically available. We evaluate our method on a 7-DOF robot arm for trajectory tracking under varying loads. Our method reduces the end-effector tracking error by 39%, compared to a 21% improvement achieved by a baseline that uses an extended Kalman filter.