Agile Robotics: Optimal Control, Reinforcement Learning, and Differentiable Simulation

TL;DR

This paper explores how optimal control, reinforcement learning, and differentiable simulation can be integrated to design highly agile and robust control algorithms for autonomous robots across diverse applications.

Contribution

It introduces a novel framework combining these methods to improve robot agility and robustness in complex, real-world scenarios.

Findings

Enhanced control algorithms for increased robot agility

Robustness against unforeseen disturbances demonstrated

Framework applicable to various robotic platforms

Abstract

Control systems are at the core of every real-world robot. They are deployed in an ever-increasing number of applications, ranging from autonomous racing and search-and-rescue missions to industrial inspections and space exploration. To achieve peak performance, certain tasks require pushing the robot to its maximum agility. How can we design control algorithms that enhance the agility of autonomous robots and maintain robustness against unforeseen disturbances? This paper addresses this question by leveraging fundamental principles in optimal control, reinforcement learning, and differentiable simulation.