Singhshivam·Oct 19Teaching an SO101 to sort blue candiesReal demonstrations, ACT, SmolVLA and an Isaac Lab experiment at B1S Hacktober Physical AI 2026
Eshwarhebsur·Oct 19Training And Benchmarking Imitation Learning Policies On Lerobot S0101 Robotic ArmBenchmarking and evaluation of foundational model such as ACT and Diffusion on a low cost Lerobot- So101 arm with minimum amount of…
Arun Murugesan·Sep 28I Taught a ₹1000 Robot Arm to Pick and Place Objects Using SmolVLA 🤖How a hobby-servo arm, an Arduino Uno, and a fine-tuned vision-language-action model ended up doing real imitation learning on a budget…
Glen Yu·Sep 1What I learned training an ACT policy for the LeRobot SO-ARM101A response icon3A response icon3
Abhijeet Kadam·Jul 6Giving AI a Pair of Hands — Part 2: Training a Robot Arm with LeRobot, SmolVLA, and Real-World…In Part 1, the focus was on the idea: giving AI physical capability — moving from software agents and LLMs into Physical AI. This second…
Abhijeet Kadam·Jun 30Giving AI a Pair of Hands: How This Physical AI Journey BeganEvery innovation has a story, and this one began with a simple school project.
AlexRoboticsExperiments·Apr 6Teaching a Robot Arm to Pick a Bottle: First Results with the Pi0.5 Imitation Learning modelA technical account of running a first imitation learning policy on real hardware — what worked, what didn’t, and what 87–93% success…
Vizuara AI·Feb 17How to run SO-101 Robotics simulations in Maniskill Environment?I am documenting my experience with the Maniskill environment in this article.
Vizuara AI·Feb 8How does ACT (Action Chunking with Transformers) actually work?The ACT architecture was first described in a paper which came out in 2023:
Mario Bergeron·Feb 2Hand Controlled Robot Car — LeKiwiRevisiting the original Hand-Controlled Robot Car demo, using the LeKiwi mobile base, setup as a digital twin.
