Toward Learning to Solve Insertion Tasks: A Developmental Approach Using Exploratory Behaviors and Proprioception

Philip Koonce, Vasha Dutell, Jose Farrington, Vladimir Sukhoy, Alexander Stoytchev

AAAI 2011 pp. 1798-1799

doi:10.1609/AAAI.V25I1.8062 /aaai/2011/koonce2011aaai-learning/

Abstract

This paper describes an approach to solving insertion tasks by a robot that uses exploratory behaviors and proprioceptive feedback. The approach was inspired by the developmental progression of insertion abilities in both chimpanzees and humans (Hayashi et al. 2006). Before mastering insertions, the infants of the two species undergo a stage where they only press objects against other objects without releasing them. Our goal was to emulate this developmental stage on a robot to see if it may lead to simpler representations for insertion tasks. Experiments were performed using a shapesorter puzzle with three different blocks and holes.

PDF AAAI Semantic Scholar

Cite

Text

Koonce et al. "Toward Learning to Solve Insertion Tasks: A Developmental Approach Using Exploratory Behaviors and Proprioception." AAAI Conference on Artificial Intelligence, 2011. doi:10.1609/AAAI.V25I1.8062

Markdown

[Koonce et al. "Toward Learning to Solve Insertion Tasks: A Developmental Approach Using Exploratory Behaviors and Proprioception." AAAI Conference on Artificial Intelligence, 2011.](https://mlanthology.org/aaai/2011/koonce2011aaai-learning/) doi:10.1609/AAAI.V25I1.8062

BibTeX

@inproceedings{koonce2011aaai-learning,
  title     = {{Toward Learning to Solve Insertion Tasks: A Developmental Approach Using Exploratory Behaviors and Proprioception}},
  author    = {Koonce, Philip and Dutell, Vasha and Farrington, Jose and Sukhoy, Vladimir and Stoytchev, Alexander},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2011},
  pages     = {1798-1799},
  doi       = {10.1609/AAAI.V25I1.8062},
  url       = {https://mlanthology.org/aaai/2011/koonce2011aaai-learning/}
}