Achieving versatile robot locomotion requires motor skills that can adapt to previously unseen situations. We propose a multi-expert learning architecture (MELA) that learns to generate adaptive skills from a group of representative expert skills. During training, MELA is first initialized by a distinct set of pretrained experts, each in a separate deep neural network (DNN). Then, by learning the combination of these DNNs using a gating neural network (GNN), MELA can acquire more specialized experts and transitional skills across various locomotion modes. During runtime, MELA constantly blends multiple DNNs and dynamically synthesizes a new DNN to produce adaptive behaviors in response to changing situations. This approach leverages the advantages of trained expert skills and the fast online synthesis of adaptive policies to generate responsive motor skills during the changing tasks. Using one unified MELA framework, we demonstrated successful multiskill locomotion on a real quadruped robot that performed coherent trotting, steering, and fall recovery autonomously and showed the merit of multi-expert learning generating behaviors that can adapt to unseen scenarios.
A novel control synthesis is proposed for humanoids to demonstrate unique foot tilting behaviors comparable to humans in balance recovery. Our study of model based behaviors explains the underlying mechanism and the significance of foot tilting well. Our main algorithms are composed of impedance control at the center of mass, virtual stoppers that prevents over-tilting of the feet, and postural control for the torso. The proof of concept focuses on the sagittal scenario and the proposed control is effective to produce human-like balancing behaviors characterized by active foot tilting. The successful replication of this behavior on a real humanoid proves the feasibility of deliberately controlled underactuation. The experimental validation was rigorously performed, and the data from the sub-modules and the entire control were presented and analyzed.
Humanoid robots are expected to achieve stable walking on uneven terrains. In this paper, a control algorithm for humanoid robots walking on previously unknown terrains with terrain estimation is proposed, which requires only minimum modification to the original walking gait. The swing foot trajectory is redesigned to ensure that the foot lands at the desired horizontal positions under various terrain height. A compliant terrain adaptation method is applied to the landing foot to achieve a firm contact with the ground. Then a terrain estimation method that takes into account the deformations of the linkages is applied, providing the target for the following correction and adjustment. The algorithm was validated through walking experiments on uneven terrains with the full-size humanoid robot Kong.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.