Learning object affordances by leveraging the combination of human-guidance and self-exploration
Authors:
- 1 March 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 221-228
Abstract
Our work focuses on robots to be deployed in human environments. These robots, which will need specialized object manipulation skills, should leverage end-users to efficiently learn the affordances of objects in their environment. This approach is promising because people naturally focus on showing salient aspects of the objects [1]. We replicate prior results and build on them to create a combination of self and supervised learning. We present experimental results with a robot learning 5 affordances on 4 objects using 1219 interactions. We compare three conditions: (1) learning through self-exploration, (2) learning from supervised examples provided by 10 naïve users, and (3) self-exploration biased by the user input. Our results characterize the benefits of self and supervised affordance learning and show that a combined approach is the most efficient and successful.Keywords
This publication has 16 references indexed in Scilit:
- Object Learning Through Active ExplorationIEEE Transactions on Autonomous Mental Development, 2013
- Socially guided intrinsic motivation for robot learning of motor skillsAutonomous Robots, 2013
- Perceiving, Learning, and Exploiting Object Affordances for Autonomous Pile Manipulation2013
- Perception and human interaction for developmental learning of objects and affordances2012
- Intrinsically Motivated Hierarchical Skill Learning in Structured EnvironmentsIEEE Transactions on Autonomous Mental Development, 2010
- Learning Object Affordances: From Sensory--Motor Coordination to ImitationIEEE Transactions on Robotics, 2008
- To Afford or Not to Afford: A New Formalization of Affordances Toward Affordance-Based Robot ControlAdaptive Behavior, 2007
- Intrinsic Motivation Systems for Autonomous Mental DevelopmentIEEE Transactions on Evolutionary Computation, 2007
- Curious model-building control systems1991
- An introduction to hidden Markov modelsIEEE ASSP Magazine, 1986