News

Paper on "Learning Causal Relationships of Object Properties and Affordances Through Human Demonstrations and Self-Supervised Intervention for Purposeful Action in Transfer Environments"


In the paper "Learning Causal Relationships of Object Properties and Affordances Through Human Demonstrations and Self-Supervised Intervention for Purposeful Action in Transfer Environments", we present a new method for learning causal relationships between object properties and object affordances which can be transferred to other environments. Our approach, implemented on a PR2 robot, generates hypotheses of property-affordance models in a toy environment based on human demonstrations that are subsequently tested through interventional experiments.
C. Uhde, N. Berberich, H. Ma, Julio Rogelio Guadarrama Olvera and Gordon Cheng, "Learning Causal Relationships of Object Properties and Affordances Through Human Demonstrations and Self-Supervised Intervention for Purposeful Action in Transfer Environments," in IEEE Robotics and Automation Letters, vol. 7, no. 4, pp. 11015-11022, Oct. 2022, doi: 10.1109/LRA.2022.3196125.