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...
Hoofdauteurs: | Gangapurwala, S, Campanaro, L, Havoutis, I |
---|---|
Formaat: | Conference item |
Taal: | English |
Gepubliceerd in: |
IEEE
2023
|
Gelijkaardige items
-
Learning and deploying robust locomotion policies with minimal dynamics randomization
door: Campanaro, L, et al.
Gepubliceerd in: (2024) -
Guided constrained policy optimization for dynamic quadrupedal robot locomotion
door: Gangapurwala, S, et al.
Gepubliceerd in: (2020) -
Learning system adaptive legged robotic locomotion policies
door: Gangapurwala, S
Gepubliceerd in: (2022) -
RLOC: terrain-aware legged locomotion using reinforcement learning and optimal control
door: Gangapurwala, S, et al.
Gepubliceerd in: (2022) -
Real-time trajectory adaptation for quadrupedal locomotion using deep reinforcement learning
door: Gangapurwala, S, et al.
Gepubliceerd in: (2021)