Robotics research

LeRobot, SmolVLA, and SO-101 Evaluation

Research tooling and model evaluation for robotic-arm autonomy, with a focus on making training, deployment, and experiment review less repetitive and more measurable.

GitHub Projects

What I built

Lab workflow tooling

I built a Visualizer inside a LeRobot GUI Wrapper so the lab could reduce repetitive command generation and inspect datasets, deployment videos, model folders, metadata, history, and experiment runs from one interface.

The wrapper sits on top of an existing LeRobot installation instead of replacing it. It helps with hardware bring-up, teleoperation, dataset recording, training, deployment, replay, history review, and experiment comparison.

Model work

Training and evaluation

I trained and evaluated multiple robotic policies for pick-and-place tasks on SO-101 arms. The model families I worked with include SmolVLA, ACT, GR00T, and PI0.5-style workflows.

Training ran on an NVIDIA A100 cluster, and the research work focused on developing environments and training conditions that improved real hardware performance instead of only producing offline metrics.

Hardware

SO-101 robotic arms

The work used 6-DOF SO-101 leader/follower robotic-arm setups for data collection and policy deployment. That meant dealing with calibration, camera setup, action chunking, dataset quality, and the difference between a model that trains and a model that completes the task on hardware.

Evidence

Current proof

Public code: LeRobot GUI Wrapper repository.
Research context: Texas A&M robotics research with Dileep Kalathil and Srinivas Shakkottai.
Evaluation task: pick-and-place performance on SO-101 robotic arms.
Next proof to add: demo video, model comparison table, and any lab-approved results.