Information-driven Affordance Discovery for Efficient Robotic Manipulation

TL;DR

This paper introduces IDA, an information-based method that accelerates the discovery of robotic affordances, reducing data needs for manipulation tasks through well-directed interactions, validated in simulation and real-world experiments.

Contribution

The paper proposes an information-driven measure to improve affordance discovery efficiency, with theoretical justification and empirical validation in both simulated and real environments.

Findings

Enhanced data efficiency in simulation for visual affordance discovery.

Successful learning of grasping affordances with minimal real-world interactions.

Improved performance in tasks like stacking and opening drawers.

Abstract

Robotic affordances, providing information about what actions can be taken in a given situation, can aid robotic manipulation. However, learning about affordances requires expensive large annotated datasets of interactions or demonstrations. In this work, we argue that well-directed interactions with the environment can mitigate this problem and propose an information-based measure to augment the agent's objective and accelerate the affordance discovery process. We provide a theoretical justification of our approach and we empirically validate the approach both in simulation and real-world tasks. Our method, which we dub IDA, enables the efficient discovery of visual affordances for several action primitives, such as grasping, stacking objects, or opening drawers, strongly improving data efficiency in simulation, and it allows us to learn grasping affordances in a small number of interactions, on a real-world setup with a UFACTORY XArm 6 robot arm.