A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf
.
Filters
Grasp stability assessment through unsupervised feature learning of tactile images
2017
2017 IEEE International Conference on Robotics and Automation (ICRA)
This paper present a novel way to improve robotic grasping: by using tactile sensors and an unsupervised feature-learning approach, a robot can find the common denominators behind successful and failed ...
In total, using a total of 54 different objects, our system recognized grasp failure 83.70% of time. ...
We proposed an approach to grasp assessment that used unsupervised feature learning to find the most relevant high-level features for distinguishing between tactile images of successful and failed picks ...
doi:10.1109/icra.2017.7989257
dblp:conf/icra/CockbumRLMD17
fatcat:krqaeksqdvcydc6mm6uavje4eu
Learning to Grasp Without Seeing
[article]
2018
arXiv
pre-print
Next, our re-grasping model learns to progressively improve grasps with tactile feedback based on the learned features. ...
To learn a representation of tactile signals, we propose an unsupervised auto-encoding scheme, which shows a significant improvement of 4-9% over prior methods on a variety of tactile perception tasks. ...
The core of our method lies in the combination of a) a simple method of touch based localization b) unsupervised learning of rich tactile features and c) a learning based method for re-grasping using haptic ...
arXiv:1805.04201v1
fatcat:2vmuz7yzsjf2pdufvjyekqlzhy
Object Detection Recognition and Robot Grasping Based on Machine Learning: A Survey
2020
IEEE Access
[72] proposed a probabilistic framework for grasp modeling and stability assessment, which integrates supervised learning and unsupervised learning, and Bayesian networks are used to model the conditional ...
As shown in Fig. 4 , the assessment of self-supervised learning ability is mainly completed through a pretraining-fine-tuning mode. ...
doi:10.1109/access.2020.3028740
fatcat:de4euqnb4ngsbclfob5izyeaxa
Self-supervised regrasping using spatio-temporal tactile features and reinforcement learning
2016
2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
First, we present a grasp stability predictor that uses spatio-temporal tactile features collected from the early-object-lifting phase to predict the grasp outcome with a high accuracy. ...
Next, the trained predictor is used to supervise and provide feedback to a reinforcement learning algorithm that learns the required grasp adjustments based on tactile feedback. ...
The newest results in the analysis of the tactile time series data for grasp stability assessment were presented in [2] . ...
doi:10.1109/iros.2016.7759309
dblp:conf/iros/ChebotarHSSS16
fatcat:wgopf4bcazh2vks7zlosp56nom
Tactile-Driven Grasp Stability and Slip Prediction
2019
Robotics
The use of tactile data is essential to check such conditions and, therefore, predict the stability of a grasp. ...
In this work, we present and compare different methodologies based on deep learning in order to represent and process tactile data for both stability and slip prediction. ...
[33] used an unsupervised feature-learning approach to find the common denominator behind successful and failed grasps in order to predict whether a grasp attempt would be successful or not. ...
doi:10.3390/robotics8040085
fatcat:kstfa4gdyran7oupcysxvkohha
Robotic tactile perception of object properties: A review
2017
Mechatronics (Oxford)
Available tactile sensing technologies are briefly presented before an extensive review on tactile recognition of object properties. ...
In an effort to collect and summarize the major scientific achievements in the area, this survey extensively reviews current trends in robot tactile perception of object properties. ...
In [119] , PCA is applied to reduce the dimensionality of tactile readings. The obtained tactile features are then used for grasp stability assessment and grasp adaptation. ...
doi:10.1016/j.mechatronics.2017.11.002
fatcat:aagspwgsw5bvreclzqrrasb6ry
Robotic Tactile Perception of Object Properties: A Review
[article]
2017
arXiv
pre-print
Available tactile sensing technologies are briefly presented before an extensive review on tactile recognition of object properties. ...
In an effort to collect and summarize the major scientific achievements in the area, this survey extensively reviews current trends in robot tactile perception of object properties. ...
In [119] , PCA is applied to reduce the dimensionality of tactile readings. The obtained tactile features are then used for grasp stability assessment and grasp adaptation. ...
arXiv:1711.03810v1
fatcat:mzdlwaktzvcifp7vrcmlvvs54m
Novel Tactile Sensor Technology and Smart Tactile Sensing Systems: A Review
2017
Sensors
There still is lack of signal processing and machine learning methods that can deal with such complicated problems [16] . ...
This paper extends previous reviews by focusing on the current state-of-the-art machine learning and signal processing technology, outstanding challenges which must be overcome, and applications of smart ...
Conflicts of Interest: The authors declare no conflict of interest. ...
doi:10.3390/s17112653
pmid:29149080
pmcid:PMC5713637
fatcat:h725jo4frbafvmijwik3hr425i
Tactile sensing in dexterous robot hands — Review
2015
Robotics and Autonomous Systems
The applications of these algorithms include grasp stability estimation, tactile object recognition, tactile servoing and force control. ...
This paper reviews current state-of-the-art of manipulation and grasping applications that involve artificial sense of touch and discusses pros and cons of each technique. ...
Grasp stability is evaluated by analyzing tactile images and hand configurations based on supervised machine learning algorithms. ...
doi:10.1016/j.robot.2015.07.015
fatcat:lifzazooinf6xefcswgzb6pshi
2021 Index IEEE Transactions on Robotics Vol. 37
2021
IEEE Transactions on robotics
The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, month, and inclusive pagination. ...
., +, TRO Feb. 2021 82-98 Towards Generalized Manipulation Learning Through Grasp Mechan-ics-Based Features and Self-Supervision. ...
., +, TRO Aug. 2021 1065-1080 Towards Generalized Manipulation Learning Through Grasp Mechanics-Based Features and Self-Supervision. ...
doi:10.1109/tro.2022.3141270
fatcat:wbcpmrap6ndprec2gtu7m2yhmy
Unplanned, model-free, single grasp object classification with underactuated hands and force sensors
2015
2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
The technique leverages the benefits of simple, adaptive robot grippers (which can grasp successfully without prior knowledge of the hand or the object model), with an advanced machine learning technique ...
The feature space used consists only of the actuator positions and the force sensor measurements at two specific time instances of the grasping process. ...
object to guarantee stability of the grasp. ...
doi:10.1109/iros.2015.7354091
dblp:conf/iros/LiarokapisCSD15
fatcat:3cunl4ffsreu3b5wghnp5ina7y
Robotics Dexterous Grasping: The Methods Based on Point Cloud and Deep Learning
2021
Frontiers in Neurorobotics
A comprehensive review of the methods based on point cloud and deep learning for robotics dexterous grasping from three perspectives is given in this paper. ...
Dexterous manipulation, especially dexterous grasping, is a primitive and crucial ability of robots that allows the implementation of performing human-like behaviors. ...
Zapata-Impata et al. ( 2017 ) presents a function to assess grasp configurations stability by considering the distance, direction and geometric shape of the grasp. ...
doi:10.3389/fnbot.2021.658280
pmid:34177509
pmcid:PMC8221534
fatcat:b33jc3vjsnd2taidrlznl3l3sq
Staged Development of Robot Skills: Behavior Formation, Affordance Learning and Imitation with Motionese
2015
IEEE Transactions on Autonomous Mental Development
The proposed framework includes a number of common features with infant sensorimotor development. ...
Finally, in the third stage, the learned structures and predictors are used to bootstrap complex imitation and action learning with the help of a cooperative tutor. ...
It was also supported in part by a contract with the Ministry of Internal Affairs and Communications, Japan, entitled, 'Novel and innovative R&D making use of brain structures'. ...
doi:10.1109/tamd.2015.2426192
fatcat:zoa2t455xbh6jitasciy2emtxq
Neural Architectures for Robot Intelligence
[article]
2004
arXiv
pre-print
Regarding the issue of learning, we propose to view real-world learning from the perspective of data mining and to focus more strongly on the imitation of observed actions instead of purely reinforcement-based ...
As examples, we report on the development of a modular system for the recognition of continuous hand postures based on neural nets, the use of vision and tactile sensing for guiding prehensile movements ...
Acknowledgement Part of this research was funded by the German Science Foundation (DFG CRC 360). ...
arXiv:cs/0410042v1
fatcat:gejxosvaljexfcizbfhy35ri2a
Modeling Grasp Motor Imagery through Deep Conditional Generative Models
[article]
2017
arXiv
pre-print
In this paper, we investigate how deep learning techniques can allow us to translate high-level concepts such as motor imagery to the problem of robotic grasp synthesis. ...
Grasping is a complex process involving knowledge of the object, the surroundings, and of oneself. ...
Instead of learning a direct, image-to-grasp mapping through neural networks, we instead learn an (image-andgrasp)-to-grasp mapping. ...
arXiv:1701.03041v1
fatcat:gvnehhhkkvfdndrhkku6puzqae
« Previous
Showing results 1 — 15 out of 335 results