Rapid and Robust Trajectory Optimization for Humanoids

TL;DR

This paper presents RAPTOR, a generalized gait optimization framework for humanoid robots that produces smooth, feasible trajectories efficiently, overcoming computational challenges and reducing reliance on initial guesses.

Contribution

The work introduces a novel, open-source trajectory optimization method that is faster, more robust, and explicitly handles kinematic constraints for humanoids.

Findings

Faster convergence than existing methods

Robust to initial guess variations

Explicitly incorporates kinematic constraints

Abstract

Performing trajectory design for humanoid robots with high degrees of freedom is computationally challenging. The trajectory design process also often involves carefully selecting various hyperparameters and requires a good initial guess which can further complicate the development process. This work introduces a generalized gait optimization framework that directly generates smooth and physically feasible trajectories. The proposed method demonstrates faster and more robust convergence than existing techniques and explicitly incorporates closed-loop kinematic constraints that appear in many modern humanoids. The method is implemented as an open-source C++ codebase which can be found at https://roahmlab.github.io/RAPTOR/.