Team Idea
Building a multimodal Vision-Language-Action (VLA) manipulation agent for simulated bimanual robotic control (Intel Track) integrated with real-time streaming voice commanding via Speechmatics.
We are pairing spatial multi-modal reasoning with low-latency trajectory planning to solve complex physical coordination challenges (like delicate tabletop manipulation) in simulation.
Looking for passionate builders experienced with PyTorch, robotic simulation environments (Gymnasium/MuJoCo/Isaac), or real-time agent orchestration. Solo-capable, but welcoming sharp contributors who want to ship a podium-worthy project.
Team Members
Ujjwal Ayush
ujjwalayush728509
Submission
Team Leader hasn't made a submission yet