Human is able to conduct 3D recognition by a limited number of haptic contacts between the target object and his/her fingers without seeing the object . This capability is defined as `haptic glance’ in cognitiveneuroscience . Most of the existing models were developed based on dense 3D data . A novel reinforcement learning based framework is proposed, where the hapticexploration procedure (the agent . iteratively predicts the next position for the robot to explore) is optimized simultaneously with the objective 3D . recognition . The model is rewarded only when the 3Dobject is accurately recognized, it is driven to find the sparse yet efficienthaptic-perceptual 3D representation of the . object . Experimental results show that our proposed model outperforms the state of the art models. Our proposed model . Our proposed models outperforms our proposed models

Author(s) : Kevin Riou, Suiyi Ling, Guillaume Gallot, Patrick Le Callet

Links : PDF - Abstract

Code :


Keywords : d - proposed - models - object - recognition -

Leave a Reply

Your email address will not be published. Required fields are marked *