Robot-object interaction requires several key perceptual building blocks including object pose estimation, object classification, and partial-object completion. These tasks form the perceptual foundation for many higher level operations including object manipulation and world-state estimation.
In real-world settings, robots will inevitably be required to interact with previously unseen objects; new approaches are required to allow for generalization across highly variable objects.
Bayesian Eigenobjects comprise a novel object representation for robots designed to facilitate this generalization. They allow a robot to observe a previously unseen object from a single viewpoint and jointly estimate that object's class, pose, and hidden geometry. The current version of our system is also capable of running in real-time on standard consumer hardware and can learn from small (as few as ~10) numbers of example objects.