Object-Oriented Learning (OOL): Perception, Representation, and Reasoning

International Conference on Machine Learning (ICML)

Friday July 17, 2020, Virtual Workshop

Access the virtual workshop page


Learning Affordances in Object-Centric Generative Models

  • Yizhe Wu, Sudhanshu Kasewa, Oliver M Groth, Sasha Salter, Li Sun, Oiwi Parker Jones, and Ingmar Posner
  • (Oral)
  • PDF · Join Meeting Room · See ICML Portal for password

The video will become available after 1st August 2020 in accordance with the ICML2020 Code of Conduct.

Given visual observations of a reaching task together with a stick-like tool, we propose a novel approach that learns to exploit task-relevant object affordances by combining generative modelling with a task-based performance predictor. The embedding learned by the generative model captures the factors of variation in object geometry, e.g. length, width, and configuration. The performance predictor identifies sub-manifolds correlated with task success in a weakly supervised manner. Using a 3D simulation environment, we demonstrate that traversing the latent space in this task-driven way results in appropriate tool geometries for the task at hand. Our results suggest that affordances are encoded along smooth trajectories in the learned latent space. Given only high-level performance criteria (such as task success), accessing these emergent affordances via gradient descent enables the agent to manipulate learned object geometries in a targeted and deliberate way.