Contact-Implicit Trajectory Optimization with Hydroelastic Contact and iLQR

TL;DR

This paper introduces a method combining iLQR with a hydroelastic contact model to improve the reliability and realism of contact-rich robot behaviors, demonstrated through quadruped locomotion and arm manipulation.

Contribution

It presents a novel integration of iLQR with hydroelastic contact modeling for scalable, physically accurate trajectory optimization in robotics.

Findings

Reliable trajectory optimization achieved with hydroelastic contact model.

Successful synthesis of quadruped locomotion and arm manipulation behaviors.

Physical experiments confirm the realism of the optimized trajectories.

Abstract

Contact-implicit trajectory optimization offers an appealing method of automatically generating complex and contact-rich behaviors for robot manipulation and locomotion. The scalability of such techniques has been limited, however, by the challenge of ensuring both numerical reliability and physical realism. In this paper, we present preliminary results suggesting that the Iterative Linear Quadratic Regulator (iLQR) algorithm together with the recently proposed pressure-field-based hydroelastic contact model enables reliable and physically realistic trajectory optimization through contact. We use this approach to synthesize contact-rich behaviors like quadruped locomotion and whole-arm manipulation. Furthermore, open-loop playback on a Kinova Gen3 robot arm demonstrates the physical accuracy of the whole-arm manipulation trajectories. Code is available at https://bit.ly/ilqr_hc and videos can be found at https://youtu.be/IqxJKbM8_ms.