Research
Across robot learning, memory, planning, and physical interaction, I ask how agents can make progress without closing off what they — or their partners — need next. The projects below are entry points into that ongoing program.
The collaborative physical intelligence architecture I proposed and lead at ZENO AI — robots that read each other's state and decide what to do next from what a partner has already started.
Read reportTwo robots can each know how to carry a sheet and still fail together. Sequential Asymmetric Imitation turns single-robot demonstrations into policies that learn to wait, yield, and recover as a partner changes the task.
View projectA useful clue can disappear from view long before a task is done. TRACE preserves causal evidence and routes it back at the branch where it matters, so a long-horizon policy can continue instead of starting over.
View projectWhen a person works through a robot, contact is information. TriPilot-FF gives hands and feet a shared interface for reach, resistance, and repositioning — so the operator can feel what the robot cannot say.
View project