2018
DOI: 10.1142/s0219843618500159
|View full text |Cite
|
Sign up to set email alerts
|

Active Tactile Exploration Based on Cost-Aware Information Gain Maximization

Abstract: Active tactile perception is a powerful mechanism to collect contact information by touching an unknown object with a robot finger in order to enable further interaction with the object or grasping of the object. The acquired object knowledge can be used to build object shape models based on such usually sparse tactile contact information. In this paper, we address the problem of object shape reconstruction from sparse tactile data gained from a robot finger that yields contact information and surface orientat… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
6
0

Year Published

2019
2019
2022
2022

Publication Types

Select...
6
3
1

Relationship

0
10

Authors

Journals

citations
Cited by 19 publications
(6 citation statements)
references
References 35 publications
0
6
0
Order By: Relevance
“…Specifically, IG assigns the most distinguishable feature with the highest information value. Currently, IG has been developed and applied to decision trees, simultaneous localization and mapping (SLAM), and feature selection techniques ( Kent, 1983 ; Lee and Lee, 2006 ) and in object shape re-construction by improving the exploration efficiency ( Ottenhaus et al, 2018 ).…”
Section: Proposed Methodologymentioning
confidence: 99%
“…Specifically, IG assigns the most distinguishable feature with the highest information value. Currently, IG has been developed and applied to decision trees, simultaneous localization and mapping (SLAM), and feature selection techniques ( Kent, 1983 ; Lee and Lee, 2006 ) and in object shape re-construction by improving the exploration efficiency ( Ottenhaus et al, 2018 ).…”
Section: Proposed Methodologymentioning
confidence: 99%
“…For instance, Driess et al [35], [45] used a compliant controller to facilitate data collection along object surfaces, and simultaneously used Gaussian Process Regression to estimate the object shape. Similar methods have also been adopted by, Rosales et al (2018) [46] and Ottenhaus et al ( 2018) [47]. While the works mentioned above indicate that simple geometric shape estimation can be accomplished through sliding sensor motion, the effectiveness of such an approach on complex object surfaces remains to be shown.…”
Section: Active Tactile Spatial Explorationmentioning
confidence: 95%
“…In addition to the approaches mentioned in the shape detection of geometric objects, the approach based on tactile perception is also a trend at present. In the research [ 116 ], the problem of shape reconstruction from sparse tactile data is studied. The Information Gain Estimation Function combines different goals as a criterion to quantify the cost-aware information gain during exploration.…”
Section: Unknown Objectsmentioning
confidence: 99%