Affordance Template Registration via Human-in-the-loop Corrections
This work addresses the need for more efficient object registration in robotics, but it appears incremental as it builds on existing Affordance Template methods with added autonomy.
The paper tackles the problem of reducing user input in registering Affordance Templates for robot manipulation by proposing a method that combines autonomous model and pose determination with user corrections, which increases autonomy compared to existing approaches.
Affordance Templates (ATs) are a method for parameterizing objects for autonomous robot manipulations. In this approach, instances of an object are registered by positioning a model in a 3D environment, which requires a large amount of user input. We instead propose a registration method which combines autonomy and user corrections. For selected objects, the system determines both the model and corresponding pose autonomously. The user makes corrections only if the model or pose is incorrect. This method increases the level of autonomy compared to existing approaches which can reduce user input and time on task. In this paper, we present an overview of existing methods, a description of our method, preliminary results, and planned future work.