Aim My Robot: Precision Local Navigation to Any Object

Publication image

Existing navigation systems mostly consider “success” when the robot reaches within 1 m radius to a goal. This precision is insufficient for emerging applications where a robot needs to be positioned precisely relative to an object for downstream tasks, such as docking, inspection, and manipulation. To this end, we design and implement Aim-My-Robot (AMR), a local navigation system that enables a robot to reach any object in its vicinity at the desired relative pose, with centimeter-level accuracy. AMR achieves high accuracy and robustness by leveraging multi-modal sensors, precise action prediction, and is trained on large-scale photorealistic data generated in simulation. AMR shows strong sim2real transfer and can adapt to different robot kinematics and unseen objects with little to no fine-tuning.

Authors

Xiangyun Meng (Applied Research Scientist at Field AI)
Sanghun Jung (University of Washington)
Sri Sadhan Jujjavarapu (Accenture)
Sanjoy Paul (Accenture)
Dieter Fox (University of Washington)

Publication Date