دورية أكاديمية
أعرض في EDS

Exploring Tactile Temporal Features for Object Pose Estimation during Robotic Manipulation.

التفاصيل البيبلوغرافية
العنوان: Exploring Tactile Temporal Features for Object Pose Estimation during Robotic Manipulation.
المؤلفون: Galaiya VR; Robotics and AI Lab, Department of Computer Science, Memorial University of Newfoundland and Labrador, St. John's, NL A1C 5S7, Canada.; Ubiquitous Computing and Machine Learning Lab, Department of Computer Science, Memorial University of Newfoundland and Labrador, St. John's, NL A1C 5S7, Canada., Asfour M; Ubiquitous Computing and Machine Learning Lab, Department of Computer Science, Memorial University of Newfoundland and Labrador, St. John's, NL A1C 5S7, Canada., Alves de Oliveira TE; Haptics and Robots Research Group, Department of Computer Science, Lakehead University, Thunder Bay, ON P7B 5E1, Canada., Jiang X; Ubiquitous Computing and Machine Learning Lab, Department of Computer Science, Memorial University of Newfoundland and Labrador, St. John's, NL A1C 5S7, Canada., Prado da Fonseca V; Robotics and AI Lab, Department of Computer Science, Memorial University of Newfoundland and Labrador, St. John's, NL A1C 5S7, Canada.
المصدر: Sensors (Basel, Switzerland) [Sensors (Basel)] 2023 May 06; Vol. 23 (9). Date of Electronic Publication: 2023 May 06.
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: MDPI Country of Publication: Switzerland NLM ID: 101204366 Publication Model: Electronic Cited Medium: Internet ISSN: 1424-8220 (Electronic) Linking ISSN: 14248220 NLM ISO Abbreviation: Sensors (Basel) Subsets: MEDLINE
أسماء مطبوعة: Original Publication: Basel, Switzerland : MDPI, c2000-
مواضيع طبية MeSH: Robotic Surgical Procedures* , Robotics*, Touch ; Hand ; Neural Networks, Computer
مستخلص: Dexterous robotic manipulation tasks depend on estimating the state of in-hand objects, particularly their orientation. Although cameras have been traditionally used to estimate the object's pose, tactile sensors have recently been studied due to their robustness against occlusions. This paper explores tactile data's temporal information for estimating the orientation of grasped objects. The data from a compliant tactile sensor were collected using different time-window sample sizes and evaluated using neural networks with long short-term memory (LSTM) layers. Our results suggest that using a window of sensor readings improved angle estimation compared to previous works. The best window size of 40 samples achieved an average of 0.0375 for the mean absolute error (MAE) in radians, 0.0030 for the mean squared error (MSE), 0.9074 for the coefficient of determination (R2), and 0.9094 for the explained variance score (EXP), with no enhancement for larger window sizes. This work illustrates the benefits of temporal information for pose estimation and analyzes the performance behavior with varying window sizes, which can be a basis for future robotic tactile research. Moreover, it can complement underactuated designs and visual pose estimation methods.
References: IEEE Trans Haptics. 2022 Dec 30;PP:. (PMID: 37015658)
Sensors (Basel). 2017 May 23;17(6):. (PMID: 28545245)
Sensors (Basel). 2022 Aug 28;22(17):. (PMID: 36080929)
Sensors (Basel). 2019 May 17;19(10):. (PMID: 31108951)
Science. 2019 Jun 21;364(6446):. (PMID: 31221831)
Soft Robot. 2018 Apr;5(2):216-227. (PMID: 29297773)
فهرسة مساهمة: Keywords: LSTM; object manipulation; pose estimation; sliding window; tactile sensing
تواريخ الأحداث: Date Created: 20230513 Date Completed: 20230515 Latest Revision: 20230515
رمز التحديث: 20231215
مُعرف محوري في PubMed: PMC10181750
DOI: 10.3390/s23094535
PMID: 37177739
قاعدة البيانات: MEDLINE
الوصف
تدمد:1424-8220
DOI:10.3390/s23094535