Recognising Affordances in Predicted Futures to Plan with Consideration of Non-canonical Affordance Effects
This work addresses planning failures in robotics or AI systems by allowing them to anticipate and exploit non-canonical effects, though it appears incremental as it builds on existing affordance and forward model concepts.
The paper tackles the problem of action sequence planning by proposing a system that combines affordance recognition with a neural forward model to predict effects, enabling it to foresee and handle non-canonical affordance effects. The system is evaluated in simulation on test tasks requiring consideration of these effects, but no concrete performance numbers are provided.
We propose a novel system for action sequence planning based on a combination of affordance recognition and a neural forward model predicting the effects of affordance execution. By performing affordance recognition on predicted futures, we avoid reliance on explicit affordance effect definitions for multi-step planning. Because the system learns affordance effects from experience data, the system can foresee not just the canonical effects of an affordance, but also situation-specific side-effects. This allows the system to avoid planning failures due to such non-canonical effects, and makes it possible to exploit non-canonical effects for realising a given goal. We evaluate the system in simulation, on a set of test tasks that require consideration of canonical and non-canonical affordance effects.