Picture

Tyler Lum @tylerlum23

CS PhD student @Stanford | Robotics & AI | Prev NVIDIA, Tesla, UBC tylerlum.github.io Palo Alto, CA Joined October 2016
  • Tweets
    32
  • Followers
    378
  • Following
    308
  • Likes
    94
Tyler Lum retweeted
robot_trainer Profile Picture

Nathan Ratliff @robot_trainer

2 months ago

The Dex team at NVIDIA is defining the bleeding edge of sim2real dexterity. Take a look below 🧵 There's a lot happening at NVIDIA in robotics, and we’re looking for good people! Reach out if you're interested. We have some big things brewing (and scaling :)

tylerlum23 Profile Picture

Tyler Lum @tylerlum23

2 months ago

We find keypoint trajectories to be a powerful interface between VLM planning & RL control VLM: Generates object + hand motion plan from a task prompt & RGB-D image (perception + commonsense) RL policy: Conditioned on the plan, learns low-level dexterous control (0-shot sim2real)

v_debakker Profile Picture

Vincent de Bakker @v_debakker

2 months ago

We find keypoint trajectories to be a powerful interface between VLM planning & RL control VLM: Generates object + hand motion plan from a task prompt & RGB-D image (perception + commonsense) RL policy: Conditioned on the plan, learns low-level dexterous control (0-shot sim2real)

Tyler Lum retweeted
kushalk_ Profile Picture

Kushal @kushalk_

2 months ago

Teleoperation is slow, expensive, and difficult to scale. So how can we train our robots instead? Introducing X-Sim: a real-to-sim-to-real framework that trains image-based policies 1) learned entirely in simulation 2) using rewards from human videos. portal-cornell.github.io/X-Sim

Tyler Lum retweeted
TheHumanoidHub Profile Picture

The Humanoid Hub @TheHumanoidHub

4 months ago

Boston Dynamics collaborated with NVIDIA to demonstrate DextrAH-RGB, a workflow for dexterous grasping from stereo RGB input. The end-to-end policy for Atlas robot, trained entirely in NVIDIA Isaac Lab, transfers zero-shot from simulation to the real robot.

Trends for United States

#UFCParis
60,5 B posts
Troy
14,9 B posts
Staub
3.722 posts
Oklahoma State
5.273 posts
#USMNT
1.452 posts
Baylor
12,8 B posts
Oregon
36,4 B posts
Ruffy
28,3 B posts
Gundy
2.306 posts
Stoops
2.325 posts
Kentucky
12,5 B posts
Imavov
22,5 B posts
Calzada
2.586 posts
Salter
1.840 posts
Karen
265 B posts
Ole Miss
6.023 posts
Julian Sayin
2.835 posts
Iowa
35,1 B posts
Billy Napier
Caio
17,5 B posts

You might like

Robot Foundation Models @physical_int
Karl Pertsch
@KarlPertsch
4K Followers
PhD Student @MPI_IS reinforcement learning for biomechanics | robotics | natural motion. MyoChallenge Organizer. @CMU_robotics visiting scholar
Pierre Schumacher
@rlfromlux
1K Followers
Research Scientist @NVIDIA. PhD student at @MMLabNTU.
Jiawei Ren
@jiawei6_ren
1K Followers
Research Scientist @ Apple  Deep Learning & AI. CS PhD. I do fast open-source RL, see https://t.co/S6VEcLFia7
Aleksei Petrenko
@petrenko_ai
1K Followers
CTO @FlexionRobotics
David Hoeller
@HoellerDavid
529 Followers
Research in robotics and simulators @NVIDIA. Building Newton https://t.co/q7OoFm5id6.
Eric Heiden
@eric_heiden
604 Followers
Building https://t.co/pLauSEgYsv to keep you healthy forever | Write https://t.co/qLeBV7BzZ1 | Always up for 🎾 & 🏋🏼
Heiki Riesenkampf
@heikirk
758 Followers
Developing algorithms for real-time reinforcement learning on robots. Research Scientist at Keen, a startup led by John Carmack. Prev ~ PhD with Richard Sutton
Khurram Javed
@KhurramJaved_96
2K Followers
Working on Gemini, @GoogleDeepMind. Human data, agents, RL. ex-@GoogleHealth.
Kelvin Zhang
@KelvZhan
428 Followers
Prof. @MIT (on leave) ; Building omics data collection engine and drug safety AI @biostate.ai ; Random musings at https://t.co/C2NpmjSraH.
Ashwin Gopinath
@ashwingop
618 Followers