Didn't think that "drones with grippers" was in the cards for a likely embodiment for pi models, but there we have it. It's literally a flying gripper. But believe it or not, pi models have been used on even stranger embodiments before...
A while ago we figured out that structure enables data-driven design: if we have data of designs + rewards, we can find a design with *higher* reward if we learn a structured function: https://t.co/HlevRSTMXV In our latest work, @kuba_AI developed a...
Back in Nov we developed Recap and trained π*-06 with RL. Now, we developed a fast *online* RL method that improves π-06 with as little as 15 min of robot data for precise tasks, using "RL tokens" exposed by our...
We made a memory system for our models at PI. We call it Multi-Scale Embodied Memory (MEM). It provides both short-term and long-term memory to enable very long tasks. We tested it on cleaning a kitchen (and yes, washing dishes),...
Check out Noriaki's thread about a way to get VLAs to run in real time with a fast "edge adapter"!
VLAs can enable vehicles to better handle complex edge cases: a VLM can "think through" a complex interaction, deduce a common sense behavior, and then a VLA can carry that out to maintain safe(r) behavior even in unusual situations.