Trajectory Optimization for Robust Humanoid Locomotion with Sample-Efficient Learning
This work addresses robustness in humanoid locomotion, which is crucial for real-world deployment, but it is incremental as it combines existing methods (trajectory optimization and Bayesian optimization) for a specific application.
The paper tackles the problem of generating robust motions for humanoid robots under uncertainties by using Bayesian optimization to find optimal cost weights in trajectory optimization, resulting in robust motions for various disturbances.
Trajectory optimization (TO) is one of the most powerful tools for generating feasible motions for humanoid robots. However, including uncertainties and stochasticity in the TO problem to generate robust motions can easily lead to an interactable problem. Furthermore, since the models used in the TO have always some level of abstraction, it is hard to find a realistic set of uncertainty in the space of abstract model. In this paper we aim at leveraging a sample-efficient learning technique (Bayesian optimization) to robustify trajectory optimization for humanoid locomotion. The main idea is to use Bayesian optimization to find the optimal set of cost weights which compromises performance with respect to robustness with a few realistic simulation/experiment. The results show that the proposed approach is able to generate robust motions for different set of disturbances and uncertainties.