Nvidia Omniverse & Jetson ambassador Dell pro precision ambassador piped.video/@kabilankb2003?s…

Bangaluru, India
reBot Duo: Sim-to-Policy Training dual-arm robots with Dell Pro Max 16 Plus + @NVIDIARobotics Jetson AGX Thor. SmolVLA fine-tuned for 20K steps, deployed at the edge! New robotics course coming soon on @seeedstudio . #Dell #NVIDIA #JetsonThor #PhysicalAI #Robotics
2
67
Tested NVIDIA GEAR ASPIRE on YAM arms in Isaac Sim. AI writes, debugs, and improves robot code without neural-network training. 🔗 research.nvidia.com/labs/gea… Aspire yam github.com/kabilankb/aspire-… #NVIDIA #Dell #DellTech #DellProPrecision
2
15
757
I typed "train the Go2" into a terminal. Minutes later, 4,096 simulated robot dogs had learned to walk, on one NVIDIA Jetson AGX Thor. Newton physics + rsl_rl PPO + a local Gemma 4 12B. No cloud, no Isaac Sim. #Dell #DellTech #DellProPrecision #nvidia medium.com/@kabilankb2003/tr…
2
1
21
1,057
I typed “train the ANYmal” and it learned to walk in ~18 minutes. One NVIDIA Jetson Thor. 4,096 parallel simulations using Newton, orchestrated by a local Gemma agent. Next: real-world deployment. 🔗 github.com/kabilankb/newton-… #Dell #NVIDIA #DellTech #DellProPrecision
2
1
16
750
Tested M3 masking (arXiv 2608.22419) on my bimanual YAM arms in Isaac Lab 3. It didn't help. Paper: 41% 63%
Mine, 50 episodes each:
ACT + M3: 11/50
Plain ACT: 12/50 20 demos is too few for masking to fix. Code: github.com/kabilankb/Isaac-L… #DellProPrecision #DellTech #NVIDIA #Dell
2
2
17
643
The new Cosmos3-Edge SO-101 on NVIDIA Jetson AGX Thor — bringing Physical AI closer to real-world robotics. Exploring the future of robot learning and evaluation with the NVIDIA Jetson AI Lab community. #NVIDIA #JetsonThor github.com/kabilankb/so101-c…
3
2
5
677
Let’s build
India’s Longest 24 Hour Physical AI Hackathon, co-hosted by Bharat1.ai and @xprobotics_ai . Hello All! This October, Bharat1.ai is bringing builders, roboticists, AI engineers, researchers, students and deeptech founders together for a series of intense 24-hour AI Hackathons in Bengaluru. B1’s Hacktober is built around one simple idea The next generation of AI will not remain confined to screens. It will take up different modalities, perceive, reason, manipulate, move and operate in the physical world. On 17 October 2026, teams of up to four will come together at Bharat1.ai to build hands-on Physical AI systems using robotic hardware, embodied intelligence workflows and modern AI tooling. Every Hackathon will begin with a dedicated Workshop, this one on Physical AI, delivered by former physical-AI and robotics researchers @nvidia , @CarnegieMellon and @iiscbangalore The workshop will help participants orient themselves on how modern robotic intelligence is being built across perception, manipulation, control, simulation and learning-based systems. Participants will get access to LeRobot SO-101 robotic arms, NVIDIA Brev Credits, technical mentorship and an environment designed specifically for experimentation. We want teams to move quickly from an idea to something that can actually make a dent in the World! The Top 3 teams will win a pair of LeRobot Arms, enabling them to continue building beyond Hacktober. Selected winning teams will also get the opportunity to pitch and demonstrate their work live at the AI & Robotics Pavilion at Bengaluru Tech Summit 2026, putting their work in front of a much larger technology, industry and innovation ecosystem. You do not need to arrive with a finished product. You need curiosity, engineering instinct and the willingness to build. B1’s Hacktober — Physical AI 2026 📅 17 October 2026 ⏱️ 24 Hours 📍 Bharat1.ai, Bengaluru 👥 Teams of up to 4 💰 ₹5,000 per team 🏆 Top 3 teams win a LeRobot Arm 🚀 Winning teams pitch live at the AI & Robotics Pavilion, @blrtechsummit 2026 We are grateful to the generous support extended from Get Set Robotics, Tanna TechBiz LLP , Solo Tech and RIC (Robotics India Community). If you have been waiting for an excuse to stop watching Physical AI from the sidelines and start building it, this is it. Builders, researchers, roboticists, founders and students, we’re ready for you. Register here: lnkd.in/gG-RGJvP More Details and Registration Details linkedin.com/posts/be-the-on…?
1
2
236
Controlling the YAM arm with LeRobot SO101—no YAM leader needed. SO101 for data collection → Cosmos for transfer → Isaac Lab for domain randomization. Running on Dell Pro Max 16 Plus + NVIDIA RTX PRO 5000 Blackwell. #Dell #DellTech #DellProPrecision #NVIDIA
6
8
93
5,858
Cosmos3 Edge Policy → SO-101 → Jetson Thor Fine-tuned to 6500 iterations for pick-Isaac Lab simulation on Dell Pro Precision RTX PRO 5000 Blackwell. GitHub: github.com/kabilankb/so101-c… HF: huggingface.co/kabilanKB/cos… #Dell #DellTech #DellProPrecision #NVIDIA
1
6
49
3,571
Real → Sim → VLA Seeed Studio reBot leader arm → NVIDIA Isaac Sim for teleoperation, data collection, and VLA training. Tutorial: seeedstudio.com/sim-to-real-… GitHub: github.com/kabilankb/rebot-i… #Dell #DellTech #DellProPrecision #NVIDIA #IsaacSim #PhysicalAI #Robotics #VLA
2
5
50
3,011
Training MicroDuck with Hermes Agent + Gemma 4 12B on a Dell Pro Precision workstation with RTX PRO 5000 Blackwell. Isaac Lab + Newton → language to action. #Dell #DellTech #DellProPrecision #NVIDIA #IsaacLab #Newton #Robotics
2
1
33
2,395
Presenting today at the Jetson AI Lab Research Meeting! I’ll be giving a lightning talk on Micro Duck with Isaac Lab & Newton on Thor. Link addevent.com/event/4xd7xmdp1…
1
6
40
2,789
MicroDuck is running! 🦆🤖 Training completed with NVIDIA Isaac Lab + Newton on a Dell Pro Precision workstation with RTX PRO 5000 Blackwell. 6,000 iterations × 4,064 parallel environments. #Dell #DellTech #DellProPrecision #NVIDIA #IsaacLab #Newton #Robotics
6
8
104
4,827
Microduck hits 1.024 m/s — 20.5 m in a single 20-second episode. Isaac Lab #Dell #DellTech #DellProPrecision #NVIDIA @huggingface @pollenrobotics @NVIDIARobotics
4
3
74
3,478
Playing in Isaac Lab RL locomotion: MuJoCo → Isaac Lab + Newton Ball-kick RL training #Dell #DellTech #DellProPrecision #NVIDIA Github: github.com/kabilankb/isaacla… @huggingface @pollenrobotics @NVIDIARobotics
1
3
45
2,565
Replying to @thelaunchd
@thelaunchd Scale 10 SO-101 episodes to 100 using the x2 reactor world model. Keep robot actions consistent while varying fruits, colors, shapes, sizes, positions, and env e.g. orange, apple, banana, mango, lemon, pear, and strawberry. Generate realistic, diverse training policy
4
7
29
1,486
@reactorworld lets start for physical ai
1
2
184