Iterative Closest Labeled Point for Tactile Object Shape Recognition
arXiv:1708.04436 · doi:10.1109/IROS.2016.7759485
Abstract
Tactile data and kinesthetic cues are two important sensing sources in robot object recognition and are complementary to each other. In this paper, we propose a novel algorithm named Iterative Closest Labeled Point (iCLAP) to recognize objects using both tactile and kinesthetic information.The iCLAP first assigns different local tactile features with distinct label numbers. The label numbers of the tactile features together with their associated 3D positions form a 4D point cloud of the object. In this manner, the two sensing modalities are merged to form a synthesized perception of the touched object. To recognize an object, the partial 4D point cloud obtained from a number of touches iteratively matches with all the reference cloud models to identify the best fit. An extensive evaluation study with 20 real objects shows that our proposed iCLAP approach outperforms those using either of the separate sensing modalities, with a substantial recognition rate improvement of up to 18%.
6 pages, 8 figures, IROS 2016
References in corpus (1)
Cited by in corpus (10)
- CNN-based Methods for Object Recognition with High-Resolution Tactile Sensors
- Knock-Knock: Acoustic Object Recognition by using Stacked Denoising Autoencoders
- Using Collocated Vision and Tactile Sensors for Visual Servoing and Localization
- 3D objects and scenes classification, recognition, segmentation, and reconstruction using 3D point cloud data: A review
- ViTac: Feature Sharing between Vision and Tactile Sensing for Cloth Texture Recognition
- Robotic Tactile Perception of Object Properties: A Review
- Surface Following using Deep Reinforcement Learning and a GelSightTactile Sensor
- 3D Shape Perception from Monocular Vision, Touch, and Shape Priors
- Spatio-temporal Attention Model for Tactile Texture Recognition
- iCLAP: Shape Recognition by Combining Proprioception and Touch Sensing