Filters








71,242 Hits in 4.8 sec

Physical Interaction as Communication: Learning Robot Objectives Online from Human Corrections [article]

Dylan P. Losey, Andrea Bajcsy, Marcia K. O'Malley, Anca D. Dragan
2021 arXiv   pre-print
Within our proposed framework human interactions become observations about the true objective. We introduce approximations to learn from and respond to pHRI in real-time.  ...  When a robot performs a task next to a human, physical interaction is inevitable: the human might push, pull, twist, or guide the robot.  ...  One-at-a-Time Online Learning We derived an update rule to learn the human's objective from their physical interactions with the robot.  ... 
arXiv:2107.02349v1 fatcat:jrlzfknk7fawdm5nymcf27fp34

Proposing ELA: Environmental Learning Algorithm for Enhancing Humans and Epigenetic Robotics Skills

Inderpal Singh
2017 International Journal of Computer Applications  
The additional benefit for utilizing epigenetic robotics is to learn new skills autonomously through social interactions from different environments.  ...  Utilizing the technique mentioned in the algorithm "ELA" (Environment Learning Algorithm), the humans will learn from machines and enhance their capabilities for better performance.  ...  learning( that is a new type of learning from the existing environment) from our social environment through real time interactions.  ... 
doi:10.5120/ijca2017915992 fatcat:wue27f6eargsbf7ylbekeqinlu

Trends of Human-Robot Collaboration in Industry Contexts: Handover, Learning, and Metrics

Afonso Castro, Filipe Silva, Vitor Santos
2021 Sensors  
goal is to achieve physical interaction, where handing over an object plays a crucial role for an effective task accomplishment.  ...  This paper provides a literature overview, defining the HRC concept, enumerating the distinct human-robot communication channels, and discussing the physical interaction that this collaboration entails  ...  To achieve a natural object transfer, the robot has to understand human intentions, by communication strategies apart from the physical contact.  ... 
doi:10.3390/s21124113 fatcat:yibzzyk2szebtotudb7cvsnex4

Interactive, Collaborative Robots: Challenges and Opportunities

Danica Kragic, Joakim Gustafson, Hakan Karaoguz, Patric Jensfelt, Robert Krug
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
Full robot autonomy, including natural interaction, learning from and with human, safe and flexible performance for challenging tasks in unstructured environments will remain out of reach for the foreseeable  ...  In the envisioned future factory setups, home and office environments, humans and robots will share the same workspace and perform different object manipulation tasks in a collaborative manner.  ...  ., 2013] , we presented a probabilistic approach for learning object models based on visual and tactile perception through physical interaction with an object.  ... 
doi:10.24963/ijcai.2018/3 dblp:conf/ijcai/KragicGKJ018 fatcat:xhg22csfwbbifausf3o5xsoh24

Learning the Correct Robot Trajectory in Real-Time from Physical Human Interactions

Dylan P. Losey, Marcia K. O'Malley
2019 ACM Transactions on Human-Robot Interaction (THRI)  
INTRODUCTION Our work seeks to leverage physical human-robot interaction (pHRI) to adapt robot behavior during the current task.  ...  The human can physically interveneby applying forces and torques-and correct the robot's behavior, such as pushing the robot towards the table or guiding the robot away from the stove.  ...  Fig. 2 . 2 Learning the correct trajectory from physical human interactions.  ... 
doi:10.1145/3354139 fatcat:mr7xqzl5y5em5auolpoev3nx4e

VRGym: A Virtual Testbed for Physical and Interactive AI [article]

Xu Xie, Hangxin Liu, Zhenliang Zhang, Yuxing Qiu, Feng Gao, Siyuan Qi, Yixin Zhu, Song-Chun Zhu
2019 arXiv   pre-print
Different from existing toolkits and virtual reality environments, the VRGym emphasizes on building and training both physical and interactive agents for robotics, machine learning, and cognitive science  ...  We propose VRGym, a virtual reality testbed for realistic human-robot interaction.  ...  VRGym supports interactions as simple as only providing visual/perception information and as sophisticated as learning complex robot grasping from human demonstrations.  ... 
arXiv:1904.01698v1 fatcat:54rrxwvxqrc7xkysrnip2hubiu

AI Meets Physical World -- Exploring Robot Cooking [article]

Yu Sun
2018 arXiv   pre-print
To best facilitate manipulation motions in the physical world, we also developed new grasping strategies for robots to hold objects with a firm grasp to withstand the disturbance during physical interactions  ...  This paper describes our recent research effort to bring the computer intelligence into the physical world so that robots could perform physically interactive manipulation tasks.  ...  We focuses on the grasp requirements derived from the voluntary and involuntary physical interactions in object manipulations.  ... 
arXiv:1804.07974v1 fatcat:m37e6wxzq5gv7m26aunyb4tuxq

Teaching NICO How to Grasp: An Empirical Study on Crossmodal Social Interaction as a Key Factor for Robots Learning From Humans

Matthias Kerzel, Theresa Pekarek-Rosin, Erik Strahl, Stefan Heinrich, Stefan Wermter
2020 Frontiers in Neurorobotics  
To overcome novel challenges in complex domestic environments, humanoid robots can learn from human teachers.  ...  To support our hypothesis, we present a Human-Robot Interaction study on human-assisted visuomotor learning with the robot NICO, the Neuro-Inspired COmpanion, a child-sized humanoid.  ...  , physical aid, learning from demonstration, and human feedback as reward signal.  ... 
doi:10.3389/fnbot.2020.00028 pmid:32581759 pmcid:PMC7297081 fatcat:y6zfse6hcffahgfsaow7uty5ve

Introduction to Journal of Human-Robot Interaction Special Issue on Haptics in HRI: Cooperation and Communication

Karon E. MacLean, Antonio Frisoli
2015 Journal of Human-Robot Interaction  
Coming generations of robots will share physical space with humans, engaging in contact interactions (physical Human Robot Interaction, or pHRI) as they carry out cooperative tasks.  ...  This special issue turns a spotlight on the specific roles that crafted haptic interaction can play in cooperation and communication between a human and a robotic partner, from the viewpoints of human  ...  To teach a robot to release an object in the right way and at the right moment as a human partner takes it, they apply realtime machine classification to data streamed from an instrumented handover object  ... 
doi:10.5898/jhri.4.1.maclean fatcat:yiycbuggs5c4tomf4tdqwfgkwu

Improving object learning through manipulation and robot self-identification

Natalia Lyubova, David Filliat, Serena Ivaldi
2013 2013 IEEE International Conference on Robotics and Biomimetics (ROBIO)  
We present a developmental approach that allows a humanoid robot to continuously and incrementally learn entities through interaction with a human partner in a first stage before categorizing these entities  ...  The interactive object learning using self-identification shows an improvement in the objects recognition accuracy with respect to learning through observation only.  ...  Categorization The categorization procedure is aimed at identifying the nature of physical entities detected in the visual space, while the robot learns objects through interaction with a human partner  ... 
doi:10.1109/robio.2013.6739655 dblp:conf/robio/LyubovaFI13 fatcat:vzrkoclz3zbqjmqwc6wsuhoota

Learning Dynamic Robot-to-Human Object Handover from Human Feedback [article]

Andras Kupcsik and David Hsu and Wee Sun Lee
2016 arXiv   pre-print
We formulate the problem as contextual policy search, in which the robot learns object handover by interacting with the human.  ...  The success of humans, however, belies the complexity of object handover as collaborative physical interaction between two agents with limited communication.  ...  This research was supported in part an A*STAR Industrial Robotics Program grant (R-252-506-001-305) and a SMART Phase-2 Pilot grant (R-252-000-571-592).  ... 
arXiv:1603.06390v1 fatcat:u6p7smslx5ezphaed3kdwcbmry

Learning and Comfort in Human–Robot Interaction: A Review

Weitian Wang, Yi Chen, Rui Li, Yunyi Jia
2019 Applied Sciences  
In this paper, we present a comprehensive review for two significant topics in humanrobot interaction: robots learning from demonstrations and human comfort.  ...  The collaboration quality between the human and the robot has been improved largely by taking advantage of robots learning from demonstrations.  ...  Section 2 provides the topic of teaching and learning in human-robot interaction, which contains discussion of robots learning from demonstration, human teaching approaches, and robot learning approaches  ... 
doi:10.3390/app9235152 fatcat:67n52vkggbhtzlfz53bz5bglna

From passive to interactive object learning and recognition through self-identification on a humanoid robot

Natalia Lyubova, Serena Ivaldi, David Filliat
2015 Autonomous Robots  
Service robots, working in evolving human environments, need the ability to continuously learn to recognize new objects.  ...  Taking inspiration from infant development, we propose a developmental approach that enables a robot to progressively learn objects appearances in a social environment: first, only through observation,  ...  robot learns appearance models of moving elements, where the motion is mostly produced by a human partner who demonstrates different objects, 2. interactive learning: the robot interacts with objects in  ... 
doi:10.1007/s10514-015-9445-0 fatcat:5y2nqhyhzjdjjaisb5b3jah4ke

A Comparative Study on Artificial Cognition and Advances in Artificial Intelligence for Social-Human Robot Interaction

Amitvikram Nawalagatti et al., Amitvikram Nawalagatti et al.,
2018 International Journal of Robotics Research and Development  
Nowadays, Social-Human Robot Interaction challenges the Artificial Intelligence in some regards include: dynamic, partly unknown atmospheres, which weren't formerly devised for robots; physical communications  ...  robot for successfully sharing tasks and space with a human.  ...  Social-Human Robot Interaction (SHRI) is an interdisciplinary analysis of communication dynamics among human beings and robots.  ... 
doi:10.24247/ijrrdjun20181 fatcat:f25uw2yn45dkhb4wzmsh64ckwq

Human-robot collaboration and machine learning: a systematic review of recent research [article]

Francesco Semeraro, Alexander Griffiths, Angelo Cangelosi
2022 arXiv   pre-print
Human-robot collaboration (HRC) is the approach that explores the interaction between a human and a robot, during the completion of a common objective, at the cognitive and physical level.  ...  Technological progress increasingly envisions the use of robots interacting with people in everyday life.  ...  presence of a human and a robot in a real physical experimental validation; 3. physical interaction between user and robot in the experimental procedure, through direct contact or mediated through an  ... 
arXiv:2110.07448v3 fatcat:mmuk2sb2mzabdpl64qiytcesny
« Previous Showing results 1 — 15 out of 71,242 results