Haptic object recognition using statistical point cloud features

Gorges, Nicolas; Navarro, Stefan Escaida; Wörn, Heinz

doi:10.1109/icar.2011.6088637

Cited by 14 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In haptic object recognition, methodologies fall into two main categories based on input type. Some methods utilize the spatial coordinates of touch points to recognize 3D shapes, often employing sensors on a robot's end effector [Allen and Roberts(1988), Zhang et al(2016), Gorges et al(2011), Kulkarni et al(2024)].…”

Section: Related Workmentioning

confidence: 99%

Bridging Realities: Training visuo-haptic object recognition models for robots using 3D virtual simulations

Ruiz,

de Jesús,

Serrano

et al. 2024

Preprint

View full text Add to dashboard Cite

This paper proposes an approach for training visuo-haptic object recognition models for robots using synthetic datasets generated by 3D virtual simulations. In robotics, where visual object recognition has witnessed considerable progress due to an abundance of image datasets, the scarcity of diverse haptic samples has resulted in a noticeable gap in research on machine learning incorporating the haptic sense. Our proposed methodology addresses this challenge by utilizing 3D virtual simulations to create realistic synthetic datasets, offering a scalable and cost-effective solution to integrate haptic and visual cues for object recognition seamlessly. Acknowledging the importance of multimodal perception, particularly in robotic applications, our research not only closes the existing gap but envisions a future where intelligent agents possess a holistic understanding of their environment derived from both visual and haptic senses. Our experiments show that synthetic datasets can be used for training object recognition in haptic and visual modes by incorporating noise, performing some preprocessing, data augmentation, or domain adaptation. This work contributes to the advancement of multimodal machine learning towards a more nuanced and comprehensive robotic perception.

show abstract

Section: Related Workmentioning

confidence: 99%

Bridging Realities: Training visuo-haptic object recognition models for robots using 3D virtual simulations

Ruiz,

de Jesús,

Serrano

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The robot can infer the shape, motion and the center of mass of the object based on the motion of the contact points measured by tactile sensors [8]. A different way of using the tactile information is using it to generate a contact point cloud and then use statistical point cloud features to provide robust descriptions of the grasped object [9]. Besides, a compact 3-D representation of unknown objects can be obtained using a probabilistic spatial approach based on Kalman filters to build a probabilistic model of the contact point cloud [10].…”

Section: Related Workmentioning

confidence: 99%

Object shape reconstruction based on the object manipulation

Montano

Suárez

2013

2013 16th International Conference on Advanced Robotics (ICAR)

View full text Add to dashboard Cite

This paper presents an approach for the object shape reconstruction based on the object manipulation using tactile information and force feedback. The tactile information collected during the manipulation process and the kinematic information of the hand are used to identify points on the surface of the object in contact with the hand and thus allowing the object shape reconstruction. Distance invariants are measured on the reconstructed object shape in order to perform the object identification. The proposed approach was implemented using the Shunck Dexterous Hand (SDH2). Different tests were performed in real executions and some examples are presented in the paper.

show abstract

“…Probabilistic methods have also been studied in multiple robotic applications, offering a robust framework for learning, perception, control and interaction [30], [31]. Probabilistic representation of tactile data and point clouds allowed the recognition of household objects in off-line mode using a fixed sequence of contact locations for exploration [32], [33]. The bag-of-features approach has been employed in different scenarios for tactile perception and identification, e.g., object identification with a tactile gripper [34].…”

Section: Related Workmentioning

confidence: 99%