Scaling-up Knowledge for a Cognizant Robot

Thomas Degris 1 Joseph Modayil 2
1 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
Department of Computing Science [Edmonton]
Abstract : This paper takes a new approach to the old adage that knowl- edge is the key for artificial intelligence. A cognizant robot is a robot with a deep and immediately accessible understand- ing of its interaction with the environment--an understand- ing the robot can use to flexibly adapt to novel situations. Such a robot will need a vast amount of situated, revisable, and expressive knowledge to display flexible intelligent be- haviors. Instead of relying on human-provided knowledge, we propose that an arbitrary robot can autonomously acquire pertinent knowledge directly from everyday interaction with the environment. We show how existing ideas in reinforce- ment learning can enable a robot to maintain and improve its knowledge. The robot performs a continual learning process that scales-up knowledge acquisition to cover a large number of facts, skills and predictions. This knowledge has seman- tics that are grounded in sensorimotor experience. We see the approach of developing more cognizant robots as a necessary key step towards broadly competent robots.
Document type :
Conference papers
Complete list of metadatas

Cited literature [10 references]  Display  Hide  Download
Contributor : Thomas Degris <>
Submitted on : Wednesday, December 12, 2012 - 4:43:38 PM
Last modification on : Wednesday, July 3, 2019 - 10:48:04 AM
Long-term archiving on : Sunday, December 18, 2016 - 12:21:01 AM


Files produced by the author(s)


  • HAL Id : hal-00764289, version 1


Thomas Degris, Joseph Modayil. Scaling-up Knowledge for a Cognizant Robot. AAAI Spring Symposium on Designing Intelligent Robots: Reintegrating AI., Mar 2012, Stanford, United States. ⟨hal-00764289⟩



Record views


Files downloads