Stanford Vision and Learning Lab
@StanfordSVL
New study that analyzes different action spaces for RL in robot manipulation in the quest to find the best one. Guys what? The best method is a combination of operational space control (1986) with learned adaptive gain tuning. To appear at #IROS2019
Animesh Garg@animesh_garg · Jun 25, 2019What action space should we use for contact-rich manipulation? We show that Variable Impedance Control in End-Effector Space outperforms most other choices.
Paper: buff.ly/2KACdq7
w\ R. Martin-Martin, @michellearning, R. Gardner, @silviocinguetta, @leto__jean
@StanfordSVL
Paper: buff.ly/2KACdq7
w\ R. Martin-Martin, @michellearning, R. Gardner, @silviocinguetta, @leto__jean
@StanfordSVL
Open quoted post →
0 3