Soft Tracking Using Contacts for Cluttered Objects to Perform Blind Object Retrieval
This addresses the challenge of blind object retrieval for robots in cluttered environments like cupboards or bins, representing a novel method for a known bottleneck.
The paper tackles the problem of retrieving objects from cluttered spaces with limited visual sensing by proposing STUCCO, a method that uses contact feedback to track objects and revise ambiguous associations, achieving at least 65% grasp success in simulations compared to baselines under 5%.
Retrieving an object from cluttered spaces suchas cupboards, refrigerators, or bins requires tracking objects with limited or no visual sensing. In these scenarios, contact feedback is necessary to estimate the pose of the objects, yet the objects are movable while their shapes and number may be unknown, making the association of contacts with objects extremely difficult. While previous work has focused on multi-target tracking, the assumptions therein prohibit using prior methods given only the contact-sensing modality. Instead, this paper proposes the method Soft Tracking Using Contacts for Cluttered Objects (STUCCO) that tracks the belief over contact point locations and implicit object associations using a particle filter. This method allows ambiguous object associations of past contacts to be revised as new information becomes available. We apply STUCCO to the Blind Object Retrieval problem, where a target object of known shape but unknown pose must be retrieved from clutter. Our results suggest that our method outperforms baselines in four simulation environments, and on a real robot, where contact sensing is noisy. In simulation, we achieve grasp success of at least 65% on all environments while no baselines achieve over 5%.