Akash Sharma

@akashshrm02

RS @ Frontier AI & Robotics (FAR), Amazon | PhD @CMU_Robotics Multimodal robot perception | Dexterous manipulation | Robot learning

San Francisco

akashsharma02.github.io

Joined May 2014

710 Following

956 Followers

Replies Reposts Media

Pinned
Akash Sharma
@akashshrm02
Jul 11
Presenting PTLD: an approach to learning tactile dexterous policies without ever simulating the tactile sensor. Tactile is essential for performing highly dexterous manipulation. However, collecting tactile observations reliably has been a fundamental bottleneck: (1)
00:00
6
Akash Sharma
@akashshrm02
Oct 16
Check this work by @BotaoUMD, @ruoshi_liu, myself and the amazing collaborators at Amazon FAR and UMD! For the first time we taught a robot to do in hand reorientation without using any simulation (I think) at all! The insight was to first learn to play, and then explore using
Ruoshi Liu
@ruoshi_liu
Oct 16
We taught a robot to play! Introducing Dexterity from Supervised Play (DSP): turning minutes of human play into a world model and dexterous manipulation policy. No task demonstrations or sim2real! play-policy.github.io
00:00
3
Akash Sharma
@akashshrm02
Oct 14
There’s more coming ;)
Andrew Carr 🤸
@andrew_n_carr
Oct 13
How is Amazon Far consistently putting out the best papers in robotics??
1
Akash Sharma
@akashshrm02
Oct 8
Object trajectory tracking is pretty sweet as an interface for policies to learn! Checkout @yulinnliu07 ‘s awesome work!
Yulin Liu
@yulinnliu07
Oct 8
🤖 For parallel-jaw grippers, high-level plans can already be executed with mature primitives such as grasping. What about dexterous hands? Introducing GOTT (General Object Trajectory Tracking): object trajectories to dexterous execution with a reusable cross-embodiment contact
00:00
Akash Sharma
@akashshrm02
Oct 1
Perhaps counterintuitive, but this is fundamentally true. IK is built on a simple model of the arm and doesn’t account for things like friction, arm dynamics, environment. With RL you can get reactivity, distill to choose the right IK branches to avoid singularities. Bitter
Qiayuan Liao
@qiayuanliao
Oct 1
Replying to @xiaolonw and @chris_j_paxton
Any online optimization (IK, ID, MPC) for low-level control should be abandoned. A RL policy can fundamentally track more precisely, more robustly, and adaptively to unknown disturbances and uncharacterized noise, especially for low-cost hardware, even on a manipulator.