Bayesian Gait Optimization for Bipedal Locomotion
نویسندگان
چکیده
One of the key challenges in robotic bipedal locomotion is finding gait parameters that optimize a desired performance metric, such as robustness or energy efficiency. Typically, gait optimization requires extensive robot experiments and specific expert knowledge. Instead, we propose to apply data-driven machine learning to automate and speed up the process of gait optimization. In particular, we use Bayesian optimization to efficiently find gait parameters that optimize the desired performance metric. As a proof of concept we demonstrate that Bayesian optimization is near-optimal in a classical stochastic optimal control framework. Moreover, we validate our approach to Bayesian gait optimization on a low-cost but sensitive real bipedal walker and show that good walking gaits can be efficiently found by Bayesian optimization.
منابع مشابه
Bayesian Optimization for Learning Gaits under Uncertainty An experimental comparison on a dynamic bipedal walker
Designing gaits and corresponding control policies is a key challenge in robot locomotion. Even with a viable controller parameterization, finding nearoptimal parameters can be daunting. Typically, this kind of parameter optimization requires specific expert knowledge and extensive robot experiments. Automatic black-box gait optimization methods greatly reduce the need for human expertise and t...
متن کاملGait Generation for a Bipedal System By Morris-Lecar Central Pattern Generator
The ability to move in complex environments is one of the most important features of humans and animals. In this work, we exploit a bio-inspired method to generate different gaits in a bipedal locomotion system. We use the 4-cell CPG model developed by Pinto [21]. This model has been established on symmetric coupling between the cells which are responsible for generating oscillatory signals. Th...
متن کاملMulti-contact bipedal robotic locomotion
This paper presents a formal framework for achieving multi-contact bipedal robotic walking, and realizes this methodology experimentally on two robotic platforms: AMBER2 and ATRIAS. Inspired by the key feature encoded in human walking— multi-contact behavior—this approach begins with the analysis of human locomotion and uses it to motivate the construction of a hybrid system model representing ...
متن کاملLocomotion in bonobos (Pan paniscus): differences and similarities between bipedal and quadrupedal terrestrial walking, and a comparison with other locomotor modes.
One of the great ongoing debates in palaeo-anthropology is when, and how, hominids acquired habitual bipedal locomotion. The newly adopted bipedal gait and the ancestral quadrupedal gait are most often considered as very distinct, with each habitual locomotor mode showing corresponding anatomical adaptations. Bonobos (Pan paniscus), along with common chimpanzees (P. troglodytes), are the closes...
متن کاملStable locomotion control of bipedal walking robots: synchronization with neural oscillators and switching control
Two novel approaches to stable legged locomotion control (neural-oscillator based control and switching control) are studied for achieving bipedal locomotion stability. Postural stability is realized by structural dynamics shaping, and gait stability is achieved by synchronization with neural oscillators and switching control. A biologically inspired control with neural oscillators (central pat...
متن کامل