Coupled Particle Filters for Robust Affordance Estimation
This addresses the challenge of robust affordance estimation for robotics, which is incremental as it builds on existing estimators with a novel coupling approach.
The paper tackled the problem of robotic affordance estimation by proposing a method that uses two coupled recursive estimators for graspable and movable regions to disambiguate visual, geometric, and semantic signals, resulting in outperforming three recent methods by 245-308% in precision and achieving a 70% success rate in real-world evaluations.
Robotic affordance estimation is challenging due to visual, geometric, and semantic ambiguities in sensory input. We propose a method that disambiguates these signals using two coupled recursive estimators for sub-aspects of affordances: graspable and movable regions. Each estimator encodes property-specific regularities to reduce uncertainty, while their coupling enables bidirectional information exchange that focuses attention on regions where both agree, i.e., affordances. Evaluated on a real-world dataset, our method outperforms three recent affordance estimators (Where2Act, Hands-as-Probes, and HRP) by 308%, 245%, and 257% in precision, and remains robust under challenging conditions such as low light or cluttered environments. Furthermore, our method achieves a 70% success rate in our real-world evaluation. These results demonstrate that coupling complementary estimators yields precise, robust, and embodiment-appropriate affordance predictions.