Zobrazeno 1 - 10
of 34
pro vyhledávání: '"Bellegarda, Guillaume"'
We present a framework for learning a single policy capable of producing all quadruped gaits and transitions. The framework consists of a policy trained with deep reinforcement learning (DRL) to modulate the parameters of a system of abstract oscilla
Externí odkaz:
http://arxiv.org/abs/2411.04787
Typical legged locomotion controllers are designed or trained offline. This is in contrast to many animals, which are able to locomote at birth, and rapidly improve their locomotion skills with few real-world interactions. Such motor control is possi
Externí odkaz:
http://arxiv.org/abs/2410.16417
This paper presents a framework for dynamic object catching using a quadruped robot's front legs while it stands on its rear legs. The system integrates computer vision, trajectory prediction, and leg control to enable the quadruped to visually detec
Externí odkaz:
http://arxiv.org/abs/2410.08065
Quadruped robots are showing impressive abilities to navigate the real world. If they are to become more integrated into society, social trust in interactions with humans will become increasingly important. Additionally, robots will need to be adapta
Externí odkaz:
http://arxiv.org/abs/2406.19893
Autor:
Sun, Ge, Shafiee, Milad, Li, Peizhuo, Bellegarda, Guillaume, Ijspeert, Auke, Sartoretti, Guillaume
Animals possess a remarkable ability to navigate challenging terrains, achieved through the interplay of various pathways between the brain, central pattern generators (CPGs) in the spinal cord, and musculoskeletal system. Traditional bioinspired con
Externí odkaz:
http://arxiv.org/abs/2404.17815
Legged robots are becoming increasingly agile in exhibiting dynamic behaviors such as running and jumping. Usually, such behaviors are either optimized and engineered offline (i.e. the behavior is designed for before it is needed), either through mod
Externí odkaz:
http://arxiv.org/abs/2403.06954
Learning a locomotion policy for quadruped robots has traditionally been constrained to a specific robot morphology, mass, and size. The learning process must usually be repeated for every new robot, where hyperparameters and reward function weights
Externí odkaz:
http://arxiv.org/abs/2310.10486
Autor:
Yu, Wanming, Yang, Chuanyu, McGreavy, Christopher, Triantafyllidis, Eleftherios, Bellegarda, Guillaume, Shafiee, Milad, Ijspeert, Auke Jan, Li, Zhibin
Robot motor skills can be learned through deep reinforcement learning (DRL) by neural networks as state-action mappings. While the selection of state observations is crucial, there has been a lack of quantitative analysis to date. Here, we present a
Externí odkaz:
http://arxiv.org/abs/2306.17101
Quadruped animals seamlessly transition between gaits as they change locomotion speeds. While the most widely accepted explanation for gait transitions is energy efficiency, there is no clear consensus on the determining factor, nor on the potential
Externí odkaz:
http://arxiv.org/abs/2306.07419
Quadruped animal locomotion emerges from the interactions between the spinal central pattern generator (CPG), sensory feedback, and supraspinal drive signals from the brain. Computational models of CPGs have been widely used for investigating the spi
Externí odkaz:
http://arxiv.org/abs/2302.13378