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...
Κύριοι συγγραφείς: | Gangapurwala, S, Campanaro, L, Havoutis, I |
---|---|
Μορφή: | Conference item |
Γλώσσα: | English |
Έκδοση: |
IEEE
2023
|
Παρόμοια τεκμήρια
Παρόμοια τεκμήρια
-
Learning and deploying robust locomotion policies with minimal dynamics randomization
ανά: Campanaro, L, κ.ά.
Έκδοση: (2024) -
Guided constrained policy optimization for dynamic quadrupedal robot locomotion
ανά: Gangapurwala, S, κ.ά.
Έκδοση: (2020) -
Learning system adaptive legged robotic locomotion policies
ανά: Gangapurwala, S
Έκδοση: (2022) -
RLOC: terrain-aware legged locomotion using reinforcement learning and optimal control
ανά: Gangapurwala, S, κ.ά.
Έκδοση: (2022) -
Real-time trajectory adaptation for quadrupedal locomotion using deep reinforcement learning
ανά: Gangapurwala, S, κ.ά.
Έκδοση: (2021)