Learning low-frequency motion control for robust and dynamic robot locomotion
Robotic locomotion is often approached with the goal of maximizing robustness and reactivity by increasing motion control frequency. We challenge this intuitive notion by demonstrating robust and dynamic locomotion with a learned motion controller executing at as low as 8 Hz on a real ANYmal C quadr...
Үндсэн зохиолчид: | Gangapurwala, S, Campanaro, L, Havoutis, I |
---|---|
Формат: | Conference item |
Хэл сонгох: | English |
Хэвлэсэн: |
IEEE
2023
|
Ижил төстэй зүйлс
Ижил төстэй зүйлс
-
Learning and deploying robust locomotion policies with minimal dynamics randomization
-н: Campanaro, L, зэрэг
Хэвлэсэн: (2024) -
Guided constrained policy optimization for dynamic quadrupedal robot locomotion
-н: Gangapurwala, S, зэрэг
Хэвлэсэн: (2020) -
Learning system adaptive legged robotic locomotion policies
-н: Gangapurwala, S
Хэвлэсэн: (2022) -
RLOC: terrain-aware legged locomotion using reinforcement learning and optimal control
-н: Gangapurwala, S, зэрэг
Хэвлэсэн: (2022) -
Real-time trajectory adaptation for quadrupedal locomotion using deep reinforcement learning
-н: Gangapurwala, S, зэрэг
Хэвлэсэн: (2021)