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...
Hlavní autoři: | Gangapurwala, S, Campanaro, L, Havoutis, I |
---|---|
Médium: | Conference item |
Jazyk: | English |
Vydáno: |
IEEE
2023
|
Podobné jednotky
-
Learning and deploying robust locomotion policies with minimal dynamics randomization
Autor: Campanaro, L, a další
Vydáno: (2024) -
Guided constrained policy optimization for dynamic quadrupedal robot locomotion
Autor: Gangapurwala, S, a další
Vydáno: (2020) -
Learning system adaptive legged robotic locomotion policies
Autor: Gangapurwala, S
Vydáno: (2022) -
RLOC: terrain-aware legged locomotion using reinforcement learning and optimal control
Autor: Gangapurwala, S, a další
Vydáno: (2022) -
Real-time trajectory adaptation for quadrupedal locomotion using deep reinforcement learning
Autor: Gangapurwala, S, a další
Vydáno: (2021)