Filters








166 Hits in 7.9 sec

Assembly, tuning, and transfer of action systems in infants and robots

Luc Berthouze, Eugene C. Goldfield
2008 Infant and Child Development  
the nervous and musculoskeletal systems and the forces acting on the body, induce organizational changes in the whole, and (2) how exploratory behaviour and selective informational signals at the timescale  ...  The paper describes how three generative principles, inspired from developmental biology and shown to underlie the dynamics of infants learning to bounce in a Jolly Jumper, were broken into a set of mechanisms  ...  Goldfield is supported by the following grants from the US National Institutes of Health: 1 R01 DC007127, 1 R43 HD047128, 1 R43 HD047128, and the Developmental Disabilities Research Center at Children's  ... 
doi:10.1002/icd.542 fatcat:4gjdepqcifh6bmqz2u73x5vyje

Developmental robotics: a survey

Max Lungarella, Giorgio Metta, Rolf Pfeifer, Giulio Sandini
2003 Connection science  
The methodology advocated is synthetic and two-pronged: on the one hand, it employs robots to instantiate models originating from developmental sciences; on the other hand, it aims to develop better robotic  ...  Developmental robotics is an emerging field located at the intersection of robotics, cognitive science and developmental sciences.  ...  Giorgio Metta and Giulio Sandini would like to thank the LIRA-Lab team for the useful discussions and inspiration provided during the preparation of the manuscript.  ... 
doi:10.1080/09540090310001655110 fatcat:u657nlgehzbtlazek5pcfydxf4

Lifelong Robot Learning [chapter]

Sebastian Thrun, Tom M. Mitchell
1995 The Biology and Technology of Intelligent Autonomous Agents  
In order to do so, robots may learn the invariants of the individual tasks and environments.  ...  Two approaches to lifelong robot learning which both capture invariant knowledge about the robot and its environments are presented.  ...  In [Mitchell and Thrun, 1995 , Thrun, 1995a , result of applying EBNN to mobile robot navigation using the CMU Xavier robot are reported.  ... 
doi:10.1007/978-3-642-79629-6_7 fatcat:gfyvm2ql25gdxgsqxko5cuou6m

Lifelong robot learning

Sebastian Thrun, Tom M. Mitchell
1995 Robotics and Autonomous Systems  
In order to do so, robots may learn the invariants of the individual tasks and environments.  ...  Two approaches to lifelong robot learning which both capture invariant knowledge about the robot and its environments are presented.  ...  In [Mitchell and Thrun, 1995 , Thrun, 1995a , result of applying EBNN to mobile robot navigation using the CMU Xavier robot are reported.  ... 
doi:10.1016/0921-8890(95)00004-y fatcat:dqxlycto4rf3lotx6ykzoqsuqq

Human-Like Arm Motion Generation: A Review

Gianpaolo Gulletta, Wolfram Erlhagen, Estela Bicho
2020 Robotics  
This paper presents a literature review of the most recent research on the generation of human-like arm movements in humanoid and manipulation robotic systems.  ...  Results show that there is a strong focus on the generation of single-arm reaching movements and biomimetic-based methods.  ...  Moreover, the dynamics of a robotic agent is also needed in applications when specific physical interactions with the environment are required.  ... 
doi:10.3390/robotics9040102 fatcat:fahjlaf6hraslknxo7ifw5o4au

Social Cognition for Human-Robot Symbiosis—Challenges and Building Blocks

Giulio Sandini, Vishwanathan Mohan, Alessandra Sciutti, Pietro Morasso
2018 Frontiers in Neurorobotics  
Mohan et al. (2014) proposed a neural episodic memory architecture for robots enabling multiple functions like recalling past experiences (based on environmental cues-objects in the environment), simulation  ...  The brain+body of each agent becomes a kind of virtual environment of the other agent and both agents interact with and share the dynamics of the common physical environment.  ...  The handling Editor and reviewer ACK declared their involvement as co-editors in the Research Topic, and their shared affiliation.  ... 
doi:10.3389/fnbot.2018.00034 pmid:30050425 pmcid:PMC6051162 fatcat:3fgxxwfzn5e4fiy6tnx2a5vlf4

Twitching in Sensorimotor Development from Sleeping Rats to Robots

Mark S. Blumberg, Hugo Gravato Marques, Fumiya Iida
2013 Current Biology  
H.G.M., and the Swiss National Science Foundation NCCR Robotics Grant to F.I.  ...  We also thank Karen Adolph, Asif Ghazanfar, Greta Sokoloff, and Alex Tiriac for helpful comments on an earlier draft of this paper.  ...  Experiments in developmental robotics have already revealed how increasingly complex movements ''can be discovered and acquired by the neural-body dynamics without pre-defined coordinated control circuits  ... 
doi:10.1016/j.cub.2013.04.075 pmid:23787051 pmcid:PMC3709969 fatcat:dznsrnht3zayvhdsf2iagyvz7y

Challenges for the policy representation when applying reinforcement learning in robotics

Petar Kormushev, Sylvain Calinon, Darwin G. Caldwell, Barkan Ugurlu
2012 The 2012 International Joint Conference on Neural Networks (IJCNN)  
A summary of the state-of-the-art reinforcement learning in robotics is given, in terms of both algorithms and policy representations.  ...  Numerous challenges faced by the policy representation in robotics are identified.  ...  ACKNOWLEDGEMENTS This work was partially supported by the AMARSi European project under contract FP7-ICT-248311, and by the PANDORA European project under contract FP7-ICT-288273.  ... 
doi:10.1109/ijcnn.2012.6252758 dblp:conf/ijcnn/KormushevCCU12 fatcat:zlwj6m6cfzhy3bjx7n2udhcbzy

Robotic locomotion combining Central Pattern Generators and reflexes

Cesar Ferreira, Cristina P. Santos
2015 2015 IEEE 4th Portuguese Meeting on Bioengineering (ENBENG)  
Primarily, a reflex controller that has to be capable of generating locomotion in a quadruped robot, based on sensory information that results from the interplay between robot and environ-ment.  ...  Therefore, stable locomotion can be achieved by simple mechanical models consisting of a mass bouncing on weightless limbs (Alexander et al., 1976) , in which the dynamics of these models resembles an  ...  For example, a corrective stepping reflex and a tonic reflex can be important to improve the robot behavior in holes and roll ramps, respectively.  ... 
doi:10.1109/enbeng.2015.7088893 fatcat:n7iaam6t7rg5hlthuak73fkrjq

Can robots make good models of biological behaviour?

B Webb
2001 Behavioral and Brain Sciences  
Seven dimensions on which simulation models can differ are defined and distinctions between them discussed: 1.  ...  The explication and justification of this approach are here placed within a framework for describing and comparing models in the behavioural and biological sciences.  ...  ACKNOWLEDGMENT We thank the National Science Foundation and the Gatsby Foundation for the support of the Telluride Workshop on Neuromorphic Engineering where this work was performed.  ... 
pmid:12412325 fatcat:xzdirg5xezamdpqc5k42qydf3m

Can robots make good models of biological behaviour?

Barbara Webb
2001 Behavioral and Brain Sciences  
Seven dimensions on which simulation models can differ are defined and distinctions between them discussed: 1. Relevance: whether the model tests and generates hypotheses applicable to biology. 2.  ...  These arguments reflect the view that biological behaviour needs to be studied and modelled in context, that is, in terms of the real problems faced by real animals in real environments.  ...  Georgio Metta, a postdoctoral associate at MIT Artificial Intelligence Lab, has been supported with a grant by DARPA as part of the "Natural Tasking of Robots Based on Human Interaction Cues" project under  ... 
doi:10.1017/s0140525x01000127 fatcat:paszkdmgg5azlplbfzfyfh3z7u

How long did it last? You would better ask a human

Francesco Lacquaniti, Mauro Carrozzo, Andrea d'Avella, Barbara La Scaleia, Alessandro Moscatelli, Myrka Zago
2014 Frontiers in Neurorobotics  
In the future, human-like robots will live among people to provide company and help carrying out tasks in cooperation with humans.  ...  Robots interacting with humans may want to see the world and tell time the way humans do: if so, they must incorporate human-like fallacy.  ...  The target decelerated from launch to bounce (blue trajectory), and it accelerated after bounce (red trajectory). Blue and red segments were not present in the actual movies.  ... 
doi:10.3389/fnbot.2014.00002 pmid:24478694 pmcid:PMC3902214 fatcat:7pjsublxtjfergbxvyevpywze4

Finding and transferring policies using stored behaviors

Martin Stolle, Christopher Atkeson
2010 Autonomous Robots  
This approach is an alternative to methods for finding policies based on value functions using dynamic programming and also to using plans based on a single desired trajectory.  ...  Atkeson Results are shown for the "Labyrinth" marble maze and the Little Dog quadruped robot. The marble maze is a difficult task which requires both fast control as well as planning ahead.  ...  Acknowledgements This material is based upon work supported in part by the National Science Foundation (NSF) under NSF Grant ECS-0325383 and the Defense Advanced Research Projects Agency Learning Locomotion  ... 
doi:10.1007/s10514-010-9191-2 fatcat:r7rof7k2hnadxnlx3cvgs6bnbe

Modular features of motor control and learning

Ferdinando A Mussa-Ivaldi
1999 Current Opinion in Neurobiology  
This work was supported by grants NS35673 and P50MH48185 from the National Institutes of Health.  ...  Acknowledgements Special thanks to Emilio Bizzi, Jennifer Stevens and Reza Shadmehr for many insightful comments.  ...  This operation is possible only through the construction of some internal representation of the dynamics of the body and of its environment.  ... 
doi:10.1016/s0959-4388(99)00029-x pmid:10607638 fatcat:toyx5fk6pzczlefcg3qvdbdrtq

Templates and anchors: neuromechanical hypotheses of legged locomotion on land

R J Full, D E Koditschek
1999 Journal of Experimental Biology  
Locomotion results from complex, high-dimensional, non-linear, dynamically coupled interactions between an organism and its environment.  ...  Locating the origin of control is a challenge because neural and mechanical systems are dynamically coupled and both play a role.  ...  Locomotion results from complex, high-dimensional, non-linear, dynamically coupled interactions between an organism and its environment (Table 1 ; H1).  ... 
pmid:10562515 fatcat:chyvfuhvzjfkdfgtzmh6oezzhq
« Previous Showing results 1 — 15 out of 166 results