[PDF][PDF] An experimental evaluation of Bayesian optimization on bipedal locomotion
International Conference on Robotics and Automation, 2014•core.ac.uk
The design of gaits and corresponding control policies for bipedal walkers is a key
challenge in robot locomotion. Even when a viable controller parametrization already exists,
finding near-optimal parameters can be daunting. The use of automatic gait optimization
methods greatly reduces the need for human expertise and time-consuming design
processes. In this paper, we experimentally evaluate Bayesian optimization for gait
optimization of a real bipedal walker. By performing more than 1800 experimental …
challenge in robot locomotion. Even when a viable controller parametrization already exists,
finding near-optimal parameters can be daunting. The use of automatic gait optimization
methods greatly reduces the need for human expertise and time-consuming design
processes. In this paper, we experimentally evaluate Bayesian optimization for gait
optimization of a real bipedal walker. By performing more than 1800 experimental …
Abstract
The design of gaits and corresponding control policies for bipedal walkers is a key challenge in robot locomotion. Even when a viable controller parametrization already exists, finding near-optimal parameters can be daunting. The use of automatic gait optimization methods greatly reduces the need for human expertise and time-consuming design processes. In this paper, we experimentally evaluate Bayesian optimization for gait optimization of a real bipedal walker. By performing more than 1800 experimental evaluations, we compare Bayesian optimization with various acquisition functions. Additionally, we study the effects of using fixed hyperparameters instead of automatically optimize them.
core.ac.uk
Showing the best result for this search. See all results