Filters








19,858 Hits in 5.6 sec

Simultaneous Multi-View Object Recognition and Grasping in Open-Ended Domains [article]

Hamidreza Kasaei, Sha Luo, Remo Sasso, Mohammadreza Kasaei
2022 arXiv   pre-print
To address this problem, we propose a deep learning architecture with augmented memory capacities to handle open-ended object recognition and grasping simultaneously.  ...  In particular, our approach takes multi-views of an object as input and jointly estimates pixel-wise grasp configuration as well as a deep scale- and rotation-invariant representation as outputs.  ...  Overview: A mixed autoencoder is designed for simultaneous multi-view object grasping and recognition tasks.  ... 
arXiv:2106.01866v3 fatcat:ksdsufscnnbqzimpitax77b7tq

Object Perception and Grasping in Open-Ended Domains [article]

S. Hamidreza Kasaei
2019 arXiv   pre-print
In my research, I mainly focus on interactive open-ended learning approaches to recognize multiple objects and their grasp affordances concurrently.  ...  Inspired by this, an autonomous robot must have the ability to process visual information and conduct learning and recognition tasks in an open-ended fashion.  ...  in open-ended domains.  ... 
arXiv:1907.10932v1 fatcat:rpggrocc6becfmjhls6ivbprd4

Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching [article]

Andy Zeng, Shuran Song, Kuan-Ting Yu, Elliott Donlon, Francois R. Hogan, Maria Bauza, Daolin Ma, Orion Taylor, Melody Liu, Eudald Romo, Nima Fazeli, Ferran Alet (+9 others)
2020 arXiv   pre-print
Exhaustive experimental results demonstrate that our multi-affordance grasping achieves high success rates for a wide variety of objects in clutter, and our recognition algorithm achieves high accuracy  ...  This paper presents a robotic pick-and-place system that is capable of grasping and recognizing both known and novel objects in cluttered environments.  ...  /1539099), NVIDIA, and Facebook for hardware, technical, and financial support.  ... 
arXiv:1710.01330v5 fatcat:yyytldcvnfbvnailib366awsg4

The State of Lifelong Learning in Service Robots: Current Bottlenecks in Object Perception and Manipulation [article]

S. Hamidreza Kasaei, Jorik Melsen, Floris van Beers, Christiaan Steenkist, Klemen Voncina
2021 arXiv   pre-print
Nowadays, robots are able to recognize various objects, and quickly plan a collision-free trajectory to grasp a target object in predefined settings.  ...  Therefore, apart from batch learning, the robot should be able to continually learn about new object categories and grasp affordances from very few training examples on-site.  ...  Inspired by this theory, service robots should approach 3D object recognition and manipulation from a long-term perspective and with emphasis on domain open-endedness.  ... 
arXiv:2003.08151v3 fatcat:ks4t3qfq3bhszgbb6lzrwwq3iq

The State of Lifelong Learning in Service Robots:

S. Hamidreza Kasaei, Jorik Melsen, Floris van Beers, Christiaan Steenkist, Klemen Voncina
2021 Journal of Intelligent and Robotic Systems  
Nowadays, robots are able to recognize various objects, and quickly plan a collision-free trajectory to grasp a target object in predefined settings.  ...  In this paper, we review a set of previously published works and discuss advances in service robots from object perception to complex object manipulation and shed light on the current challenges and bottlenecks  ...  from a long-term perspective and with emphasis on domain open-endedness.  ... 
doi:10.1007/s10846-021-01458-3 fatcat:eeunivdvmrcg3piyx3r3pdsviq

Robotic pick-and-place of novel objects in clutter with multi-affordance grasping and cross-domain image matching

Andy Zeng, Shuran Song, Kuan-Ting Yu, Elliott Donlon, Francois R. Hogan, Maria Bauza, Daolin Ma, Orion Taylor, Melody Liu, Eudald Romo, Nima Fazeli, Ferran Alet (+9 others)
2019 The international journal of robotics research  
Exhaustive experimental results demonstrate that our multi-affordance grasping achieves high success rates for a wide variety of objects in clutter, and our recognition algorithm achieves high accuracy  ...  This article presents a robotic pick-and-place system that is capable of grasping and recognizing both known and novel objects in cluttered environments.  ...  This paper is a revision of a paper appearing in the proceedings of the 2018 International Conference on Robotics and Automation (Zeng et al., 2018b) .  ... 
doi:10.1177/0278364919868017 fatcat:tjzvct4y7rfnfiqk5bhlegpiwi

Exploring augmented grasping capabilities in a multi-synergistic soft bionic hand

Cristina Piazza, Ann M. Simon, Kristi L. Turner, Laura A. Miller, Manuel G. Catalano, Antonio Bicchi, Levi J. Hargrove
2020 Journal of NeuroEngineering and Rehabilitation  
Recently, the translation of neuroscientific theories (i.e. postural synergies) in software and hardware architecture of artificial devices is opening new approaches for the design and control of upper-limb  ...  Following these emerging principles, previous research on the SoftHand Pro, which embeds one physical synergy, showed promising results in terms of intuitiveness, robustness, and grasping performance.  ...  session first hand motions practiced were power grasp/hand open and then fine pinch/hand open.  ... 
doi:10.1186/s12984-020-00741-y pmid:32843058 fatcat:ssqohhjjifd4fjjgptqvf6q4y4

Interactive Open-Ended Learning for 3D Object Recognition [article]

S. Hamidreza Kasaei
2019 arXiv   pre-print
Inspired by this capability, we seek to create a cognitive object perception and perceptual learning architecture that can learn 3D object categories in an open-ended fashion.  ...  The thesis contributes in several important ways to the research area of 3D object category learning and recognition.  ...  In this chapter, the subject of online 3D object category learning and recognition in open- ended robotic domains is investigated.  ... 
arXiv:1912.09539v1 fatcat:aksfik7earfafpe7n5amsehc2e

Task-Specific Sensor Planning for Robotic Assembly Tasks

Guy Rosman, Changhyun Choi, Mehmet Dogar, John W. Fisher IIIl, Daniela Rus
2018 2018 IEEE International Conference on Robotics and Automation (ICRA)  
When performing multi-robot tasks, sensory feedback is crucial in reducing uncertainty for correct execution.  ...  We show how they can be incorporated into a multi-robot planner, and demonstrate results with a team of robots performing assembly tasks.  ...  In recent years, the spread of RGB-D sensors has made them reliable and robust sources for many applications in robotics such as object localization [2] , [13] , object recognition [25] , and Simultaneous  ... 
doi:10.1109/icra.2018.8460194 dblp:conf/icra/RosmanCDFR18 fatcat:qbekvoqeqncljmc7zusk4uvoc4

OrthographicNet: A Deep Transfer Learning Approach for 3D Object Recognition in Open-Ended Domains [article]

Hamidreza Kasaei
2020 arXiv   pre-print
In this work, we present OrthographicNet, a Convolutional Neural Network (CNN)-based model, for 3D object recognition in open-ended domains.  ...  Experimental results show that our approach yields significant improvements over the previous state-of-the-art approaches concerning object recognition performance and scalability in open-ended scenarios  ...  CONCLUSION In this paper, we propose a deep transfer learning based approach for 3D object recognition in open-ended domains named OrthographicNet.  ... 
arXiv:1902.03057v3 fatcat:vmq5alktivfqdm46wtijqvrzvm

Robotic Grasping from Classical to Modern: A Survey [article]

Hanbo Zhang, Jian Tang, Shiguang Sun, Xuguang Lan
2022 arXiv   pre-print
By reviewing the history of robotic grasping, we want to provide a complete view of this community, and perhaps inspire the combination and fusion of different ideas, which we think would be helpful to  ...  Finally, we discuss the open problems and the future research directions that may be important for the human-level robustness, autonomy, and intelligence of robots.  ...  From this view, end-to-end learning also shares a similar idea as samplingbased methods.  ... 
arXiv:2202.03631v1 fatcat:xkwyelt5tfd5jnkhjkgxqlkevq

Improving Classification by Improving Labelling: Introducing Probabilistic Multi-Label Object Interaction Recognition [article]

Michael Wray, Davide Moltisanti, Walterio Mayol-Cuevas, Dima Damen
2017 arXiv   pre-print
For the task of object interaction recognition, often captured using an egocentric view, we show that semantic ambiguities in verbs and recognising sub-interactions along with concurrent interactions result  ...  in legitimate class overlaps (Figure 1).  ...  10 verbs, for example pour in 'Crack Egg', grasp in 'Open Fridge' and grab in 'Take Bowl'.  ... 
arXiv:1703.08338v2 fatcat:a6rl5iglw5cdrdbszwz6kcvjpe

Cloud Robotic Architectures: Directions for Future Research from a Comparative Analysis

Viraj Dawarka, Girish Bekaroo
2018 2018 International Conference on Intelligent and Innovative Computing Applications (ICONIC)  
An open access repository of Middlesex University research http://eprints.mdx.ac.uk Dawarka, Viraj and Bekaroo, Girish ORCID: https://orcid.org/0000-0003-1753-4300 (2018) Cloud robotic architectures: directions  ...  Online and Offline system of Cloud & Robot grasping architecture • Cloud (Google Object Recognition Engine, Google Cloud Storage, Grasp Analysis) • Robots (Camera, Label, Domain Knowledge  ...  [4] presented a system architecture for Cloud-Based object recognition and grasping, consisting of two phases, namely, the offline and the online.  ... 
doi:10.1109/iconic.2018.8601264 fatcat:gsbftbozlbgnxkvpcmux336bj4

HERB: a home exploring robotic butler

Siddhartha S. Srinivasa, Dave Ferguson, Casey J. Helfrich, Dmitry Berenson, Alvaro Collet, Rosen Diankov, Garratt Gallagher, Geoffrey Hollinger, James Kuffner, Michael Vande Weghe
2009 Autonomous Robots  
and other constrained objects using caging grasps, grasp planning and execution in clutter, and manipulation on pose and torque constraint manifolds.  ...  We present new algorithms for searching for objects, learning to navigate in cluttered dynamic indoor scenes, recognizing and registering objects accurately in high clutter using vision, manipulating doors  ...  Object classification In GATMO, observations are clustered and classified as observed objects in a multi-level hypothesis hierarchy.  ... 
doi:10.1007/s10514-009-9160-9 fatcat:yo25gfaotraqva7q5gyhymhss4

Lifelong 3D Object Recognition and Grasp Synthesis Using Dual Memory Recurrent Self-Organization Networks [article]

Krishnakumar Santhakumar, Hamidreza Kasaei
2022 arXiv   pre-print
In this paper, we proposed a hybrid model architecture consists of a dynamically growing dual-memory recurrent neural network (GDM) and an autoencoder to tackle object recognition and grasping simultaneously  ...  Experiment results demonstrated that the proposed model can learn both object representation and grasping simultaneously in continual learning scenarios.  ...  and recognize the objects in open-ended domains.  ... 
arXiv:2109.11544v2 fatcat:44zgnmobvbh7rlhrqumtgexqr4
« Previous Showing results 1 — 15 out of 19,858 results