Real-time Model Predictive Control and System Identification Using Differentiable Physics Simulation

TL;DR

This paper introduces a real-time differentiable physics simulation framework that enables simultaneous online system identification and optimal control, allowing robots to adapt swiftly to changing environments and reduce the sim-to-real gap.

Contribution

The paper presents a novel differentiable physics simulation approach for online system identification and control, improving robot adaptability in dynamic real-world settings.

Findings

Effective real-time adaptation to changing environments

Improved sample efficiency in control and identification

Favorable results compared to baseline methods

Abstract

Developing robot controllers in a simulated environment is advantageous but transferring the controllers to the target environment presents challenges, often referred to as the "sim-to-real gap". We present a method for continuous improvement of modeling and control after deploying the robot to a dynamically-changing target environment. We develop a differentiable physics simulation framework that performs online system identification and optimal control simultaneously, using the incoming observations from the target environment in real time. To ensure robust system identification against noisy observations, we devise an algorithm to assess the confidence of our estimated parameters, using numerical analysis of the dynamic equations. To ensure real-time optimal control, we adaptively schedule the optimization window in the future so that the optimized actions can be replenished faster than they are consumed, while staying as up-to-date with new sensor information as possible. The constant re-planning based on a constantly improved model allows the robot to swiftly adapt to the changing environment and utilize real-world data in the most sample-efficient way. Thanks to a fast differentiable physics simulator, the optimization for both system identification and control can be solved efficiently for robots operating in real time. We demonstrate our method on a set of examples in simulation and show that our results are favorable compared to baseline methods.