Sudharshan Suresh
@Suddhus
Followers
989
Following
3K
Media
40
Statuses
272
Research Scientist @BostonDynamics Atlas. Teaching humanoids a few tricks. Prev: @AIatMeta and PhD at @CMU_Robotics.
Cambridge, MA
Joined April 2009
I'm a featured interview in our latest behind-the-scenes release! We break down the ML and perception that drives the whole-body manipulation behaviors from last year. It starts with a neat demo of Atlas's range-of-motion and our vision foundation models.
5
7
51
RT @haldar_siddhant: Current robot policies often face a tradeoff: they're either precise (but brittle) or generalizable (but imprecise).….
0
75
0
I'll be speaking at the RSS Dexterous Manipulation Workshop tomorrow, discussing our recent work with Atlas!.
We are excited to host the 3rd Workshop on Dexterous Manipulation at RSS tomorrow!. Join us at OHE 122 starting at 9:00 AM! See you there!
0
3
18
RT @GeneralistAI_: Today we're excited to share a glimpse of what we're building at Generalist. As a first step towards our mission of maki….
0
136
0
RT @ZhaoMandi: How to learn dexterous manipulation for any robot hand from a single human demonstration?. Check out DexMachina, our new RL….
0
102
0
Our team also put together a great blogpost: We talk about supervised learning for 2D keypoints, foundation models for object masks, render-and-compare for object pose, and SuperTracker—our real-time smoother that combines vision, kinematics, and force.
0
1
11
Check out the awesome follow-up to sparsh by @akashshrm02 and others - self-supervised learning for a variety of downstream tasks with tactile skins!.
Robots need touch for human-like hands to reach the goal of general manipulation. However, approaches today don’t use tactile sensing or use specific architectures per tactile task. Can 1 model improve many tactile tasks?.🌟Introducing Sparsh-skin: 1/6
0
0
8
Honored to be a part of the RSS Pioneers cohort this year - look forward to catching up with folks in Los Angeles! 🤖.
List of 33 #RSSPioneer2025 is out! Their research interests cover fundamental robot design, modelling and control, robot perception and learning, localisation and mapping, human-robot interaction, healthcare and medical robotics, and soft robots! .
2
0
16
RT @LerrelPinto: So excited for this!!! . The key technical breakthrough here is that we can control joints and fingertips of the robot **w….
0
14
0
RT @XiaoyangWu_: 📢Sonata: Self-Supervised Learning of Reliable Point Representations📢. Meet Sonata, our"3D-DINO" pre-trained with Point Tra….
0
50
0
RT @BostonDynamics: Atlas is demonstrating reinforcement learning policies developed using a motion capture suit. This demonstration was de….
0
5K
0
RT @jackyliang42: Finally able to share what we've been working on the past few months 🤖🧠🖐️ . We gave Gemini the ability to perceive, reaso….
0
7
0
RT @BostonDynamics: We’re designing Atlas to do anything and everything, but we get there one step at a time. See why we started with part….
0
439
0
RT @eric_dexheimer: We’ve had fun testing the limits of MASt3R-SLAM on in-the-wild videos. Here’s the drone video of a Minnesota bowling al….
0
22
0
🎅🤸.
Wishing you a holiday season full of light and laughter as we flip over into the new year!
1
0
20
RT @rmurai0610: Introducing MASt3R-SLAM, the first real-time monocular dense SLAM with MASt3R as a foundation. Easy to use like DUSt3R/MA….
0
260
0
CMU covered our work on the Robotics Institute website!.
Check out CMU’s collab with Meta in Science Robotics! . Congrats to 2024 Ph.D. graduate Sudharshan Suresh and Professor Michael Kaess for their incredible work! . Read more about the project:
1
4
66
RT @lucacarlone1: Pre-release of part 1 of our handbook: from SLAM to Spatial Intelligence. Please provide comments and suggestions to make….
0
10
0