The controller is learnt in simulation using an inverted pendulum model and the control policy transferred and tested on two small physical humanoid robots.

Abstract—We learn a controller for a flat-footed bipedal robot to optimally respond to both (1) external disturbances caused.

This paper explores a less well studied approach to biped locomotion using model-based multigoal reinforcement learning and applies this approach to learn ...

In this work, we propose an online learning technique that learns how to step onto a reference footstep location while maintaining the balance of a bipedal ...

This paper proposes an approach for combining simulations and real experiments to learn gait stabilization parameters using a Bayesian optimization method ...

Learning ankle-tilt and foot-placement control for flat-footed bipedal balancing and walking. Conference Paper. Full-text available. Oct 2011.

Oct 20, 2022 · This paper presents an adaptive ankle impedance control method with the support of the advances of adaptive fuzzy inference systems.

Sep 27, 2019 · This paper describes the design, implementation, and experimental results of a robust balance-control framework for the stable walking of a humanoid robot on ...

The stepping control, which adjusts the footstep position or step time in an adaptive manner to disturbances, has greatly improved the balancing performance ...

This work provides a stability criterion for flat-footed bipedal locomotion and allows model-based control methods to function on homogeneous deformable ...