Vignesh Rajmohan

Robotics + AI - Currently building something new! - Previously at Google Robotics and MS and BS in ECE @ CMU

Lumi: AI Robot Desklamp

An LLM robotics experiment for using code as a policy for grounding robot actions. Also Lumi has 2 dof.

Sketching the Future

Developed a method to apply Conditional Control Techniques to Text-to-Video Models

Visibility Graph Convex Partitioning

Created a novel partitioning method for polygonal obstacle-filled 2D environments to speed up planning using Graphs of Convex Sets (GCS) by replacing the currently used IRIS partitioning method, allowing for real-time planning capabilities.


Developed unsupervised deep learning method in Pytorch for discovering and learning robot skills from unlabeled video demos of human behavior. Evaluated by tasking delta robot with imitating human demos.

1x1: Package Re-identification

Backed by PearVC startup, developed system to re-identify packages using multiple visual features: color histogram, contrastive encoding, and package dimensions.


An iOS application written in Python that allows users to leave a digital “thread” when travelling using GPS data and record visual landmarks using photos to document the route and get accurate directions back to the start location.