Balakumar Sundaralingam (@balakumar_) profile picture

Research @NVIDIA | cuRobo Lead | views my own

San Francisco, CA
Joined October 2018
Photo by Balakumar Sundaralingam (@balakumar_)Photo by Balakumar Sundaralingam (@balakumar_)Photo by Balakumar Sundaralingam (@balakumar_)Photo by Balakumar Sundaralingam (@balakumar_)Photo by Balakumar Sundaralingam (@balakumar_)Photo by Balakumar Sundaralingam (@balakumar_)Photo by Balakumar Sundaralingam (@balakumar_)Photo by Balakumar Sundaralingam (@balakumar_)Photo by Balakumar Sundaralingam (@balakumar_)
Balakumar Sundaralingam retweeted
We are giving out $500k and free YAM arms to academic teams to design dexterous manipulation benchmarks and run real-world evaluations. General-purpose robots could soon be in homes and data centers. Society should know what robots can do before they get there.
33
37
9
380
95,520
Balakumar Sundaralingam retweeted
a product can be a robot but a robot isn’t necessarily a product in time people will understand
10
8
2
136
10,169
Balakumar Sundaralingam retweeted
Let's meet and chat at #CVPR! Come by our poster or schedule a coffee chat🙌 Fri afternoon: - Fast-FoundationStereo: nvlabs.github.io/Fast-Founda… - CARI4D: nvlabs.github.io/CARI4D/ (w/ @XianghuiXie ) Sat morning: - Event6D: chohoonhee.github.io/Event6D… (w/ Jae-Young)
19
151
8,797
Balakumar Sundaralingam retweeted
Use both: web.mit.edu/dimitrib/www/Les… TO is a Newton step on the Bellman equation. Policies and value functions are "memories" of past solutions; TO should be optimizing over them at inference time. Best of both worlds. Some of the strongest RL methods do this.
Should legged robot use RL or trajectory optimization? #icra2024
3
29
3
179
24,392
Balakumar Sundaralingam retweeted
New work on vectorizing geometric fabric controllers for RL workflows at scale. DeXtreme: Fabric Guided Policies (FGP). Policies are hard on hardware. We need low-level controllers at deployment, which means we need them during training. FGPs increase hardware lifetime, enable quick iteration on training and deploying policies, and allow us to inject useful inductive bias into the system.
3
15
3
71
16,101
Balakumar Sundaralingam retweeted
DeXtreme is our new work on scaling sim-to-real for contact-rich manipulation with a vision-based state estimation on a robot hand with the infrastructure we have been developing with Isaac Gym over the past one year. arxiv.org/abs/2210.13702 dextreme.org/
3
40
18
265
Balakumar Sundaralingam retweeted
I'm excited to share our #RSS2022 workshop paper: Neural Motion Fields: Encoding Grasp Trajectories as Implicit Value Functions. w/ @Adithya_Murali_ , @balakumar_ , Wei Yang, @animesh_garg, and Dieter Fox at @nvidia. Paper: arxiv.org/abs/2206.14854 Video: youtu.be/B-pEhT1pi-Q
2
25
3
115
Balakumar Sundaralingam retweeted
Factory: Fast Contact for Robotic Assembly, our recent work, is a set of simulation methods & robot learning tools for contact-rich interactions for robotic assembly. It will be presented at RSS next month. Paper: arxiv.org/abs/2205.03532 Website: sites.google.com/nvidia.com/…
6
62
13
345
Balakumar Sundaralingam retweeted
Update on Robotic Conferences due to Coronavirus: RSS -> virtual conference WAFR -> postponed by one year (to June 2021) ICRA -> decision on April 6th (virtual vs. postpone to end of 2020) IROS -> as planned (Oct 2020) Humanoids -> as planned (Dez 2020)
1
10
24
Balakumar Sundaralingam retweeted
Spent the last two days crisscrossing Mumbai for meetings. All those autonomous miles in Chandler, Arizona are easily going to generalize for AV roll outs here. Yeah, right.
7
11
2
107
Balakumar Sundaralingam retweeted
I saw this robotics scientist working today. Commenting his code. Writing unit tests. Testing in simulation first. Operating the robot with his hand on the e-stop, observing carefully. Like a psychopath.
4
7
1
62
Balakumar Sundaralingam retweeted
I am co-organizing Women in Robotics V, taking place on June 23rd at RSS 2019 in Freiburg. We are accepting contributions for two poster sessions to encourage the participation of young female robotics researchers, offering travel grants. More info here: sites.google.com/view/rss201…
9
1
19
Balakumar Sundaralingam retweeted
Some of the YCB objects in our lab are thrown as trash by a new intern😂😂 Wonder if it possible to just buy these missing items....
1
6
Balakumar Sundaralingam retweeted
I don’t like the term “work-life balance” because it implies “balance” is something we can achieve and then be set. Instead, I recognize there are lots of things I want to do - some for work and some personal. I focus on budgeting my time in a way that I feel happy with each day.
16
33
5
301
Balakumar Sundaralingam retweeted
@oletaknowsstuff @Dr_KatieG1 @AJSantiagoLopez @BezaTuga @SusannaLHarris @Ph_D_epression @Migz614 @YouGoChi @ndchiappini @AlecAstrochem @SnarkDivine There’s no way to list all, but these are a few of the many students/postdocs who have a powerful voice here on #AcademicTwitter
4
9
1
46
Balakumar Sundaralingam retweeted
As someone who spent many years on the fringes of this diagram, searching for that little red square and thinking I’d never find it or couldn’t have it, I will say it’s worth persevering for. Also, important to note the circles are constantly shifting, so keep looking.
Saw this recently. Great way to think about which circle you find yourself in today!
4
54
2
236
Balakumar Sundaralingam retweeted
Do you nod during a class, lecture, speech, or conversation to show understanding/validate the speaker? If so, KEEP IT UP. TEACH OTHERS THE POWER OF THE NOD. YOU'RE AN AMAZING HUMAN BEING.
100
552
225
3,017
Balakumar Sundaralingam retweeted
SimBenchmark: benchmark results of contact simulation on the state-of-the-art physics engines for various robotic tasks. leggedrobotics.github.io/Sim…
1
26
3
105