Combining Simulations and Real-robot Experiments for Bayesian Optimization of Bipedal Gait Stabilization
This addresses the challenge of efficiently optimizing bipedal gait stabilization for robotics, though it appears incremental as it builds on existing Bayesian optimization methods.
The paper tackled the problem of tuning walking controller parameters by combining cheap simulations with expensive real-robot experiments, using Bayesian optimization to select informative points based on cost function entropy, and demonstrated effectiveness on the igus Humanoid Open Platform.
Walking controllers often require parametrization which must be tuned according to some cost function. To estimate these parameters, simulations can be performed which are cheap but do not fully represent reality. Real-robot experiments, on the other hand, are more expensive and lead to hardware wear-off. In this paper, we propose an approach for combining simulations and real experiments to learn gait stabilization parameters. We use a Bayesian optimization method which selects the most informative points in parameter space to evaluate based on the entropy of the cost function to optimize. Experiments with the igus Humanoid Open Platform demonstrate the effectiveness of our approach.