Learning by Experience and by Imitation in Multi-Robot Systems

Barrios-Aranibar, Dennis; Gonçalves, Luiz Marcos Garcia; Alsina, Pablo Javier

doi:10.5772/5448

Cited by 3 publications

(1 citation statement)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…18,26,27 Mixing imitation learning with RL produces a set of bene¯ts, as claimed by Barrios. 28 It diminishes the computational time of convergence, since the search space is reduced. The innovation is based on actions that the robot has observed, so it is easier to improve this behavior.…”

Section: Learning From Demonstration and Skill Innovation In Robotsmentioning

confidence: 99%

Full-Body Postural Control of a Humanoid Robot with Both Imitation Learning and Skill Innovation

González-Fierro

Balaguer

Swann

et al. 2014

Int. J. Human. Robot.

View full text Add to dashboard Cite

In this paper, we present a novel methodology to obtain imitative and innovative postural movements in a humanoid based on human demonstrations in a di®erent kinematic scale. We collected motion data from a group of human participants standing up from a chair. Modeling the human as an actuated 3-link kinematic chain, and by de¯ning a multiobjective reward function of zero moment point and joint torques to represent the stability and e®ort, we computed reward pro¯les for each demonstration. Since individual reward pro¯les show vari-ability across demonstrating trials, the underlying state transition probabilities were modeled using a Markov chain. Based on the argument that the reward pro¯les of the robot should show the same temporal structure of those of the human, we used di®erential evolution to compute a trajectory that ¯ts all humanoid constraints and minimizes the di®erence between the robot reward pro¯le and the predicted pro¯le if the robot imitates the human. Therefore, robotic imitation involves developing a policy that results in a temporal reward structure, matching that of a group of human demonstrators across an array of demonstrations. Skill innovation was achieved by optimizing a signed reward error after imitation was achieved. Experimental results using the humanoid HOAP-3 are shown.

show abstract

Section: Learning From Demonstration and Skill Innovation In Robotsmentioning

confidence: 99%

Full-Body Postural Control of a Humanoid Robot with Both Imitation Learning and Skill Innovation

González-Fierro

Balaguer

Swann

et al. 2014

Int. J. Human. Robot.

View full text Add to dashboard Cite

show abstract

A novel hybrid learning technique applied to a self-learning multi-robot system

Desouky

Schwartz

2009

2009 IEEE International Conference on Systems, Man and Cybernetics

View full text Add to dashboard Cite

A novel technique to design a fuzzy logic controller using Q(λ)-learning and genetic algorithms in the pursuit-evasion game

Desouky

Schwartz

2009

2009 IEEE International Conference on Systems, Man and Cybernetics

View full text Add to dashboard Cite

Learning by Experience and by Imitation in Multi-Robot Systems

Cited by 3 publications

References 45 publications

Full-Body Postural Control of a Humanoid Robot with Both Imitation Learning and Skill Innovation

Full-Body Postural Control of a Humanoid Robot with Both Imitation Learning and Skill Innovation

A novel hybrid learning technique applied to a self-learning multi-robot system

A novel technique to design a fuzzy logic controller using Q(λ)-learning and genetic algorithms in the pursuit-evasion game

Contact Info

Product

Resources

About

Learning by Experience and by Imitation in Multi-Robot Systems

Cited by 3 publications

References 45 publications

Full-Body Postural Control of a Humanoid Robot with Both Imitation Learning and Skill Innovation

Full-Body Postural Control of a Humanoid Robot with Both Imitation Learning and Skill Innovation

A novel hybrid learning technique applied to a self-learning multi-robot system

A novel technique to design a fuzzy logic controller using Q(&#x03BB;)-learning and genetic algorithms in the pursuit-evasion game

Contact Info

Product

Resources

About

A novel technique to design a fuzzy logic controller using Q(λ)-learning and genetic algorithms in the pursuit-evasion game