Jeannette Bohg
@leto__jean
Associate Professor @StanfordAILab @StanfordIPRL. Perception, learning and control for autonomous robotic manipulation #BlackLivesMatter# she/her 🌈
Joined May 2017
537 Following 8.6K Followers
Every roboticist has cursed a coordinate frame at 2am. There are just so many: world, base, tool, task, camera ...
Our work learns which one to trust.
Long horizon bimanual mobile manipulation requires reasoning in many coordinate frames: base, L/R hands, etc. In which frame would policy work best?
It really depends, so don’t pick. Mixture of Frames Policy: denoise in multiple frame in parallel.
🌐 (1/9)
Show more
