Shared Autonomy for Human-Robot Teams
Implicit coordination and wearable sensing that let humans and robots share one exploration task without explicit commands.
We develop interfaces and coordination frameworks in which neither the human nor the robot is fully in charge — autonomy is shared, and coordination emerges from observing each other rather than from explicit commands.
In SSRR 2022, we proposed a methodology that implicitly coordinates exploration goals between a human and an aerial robot. By tracking the human’s viewpoint direction through helmet-mounted depth sensors, the robot infers where its teammate is already looking and biases its own exploration frontier toward disjoint regions. The result is a shared-autonomy loop — the human explores naturally, the robot fills in the gaps, and the team maximizes search efficiency without a single explicit command being issued.
