Human-Inspired Topological Representations for Visual Object Recognition in Unseen Environments
This work addresses robust object recognition for low-cost robots in challenging environments, representing an incremental improvement over prior approaches.
The authors tackled visual object recognition in unseen, cluttered indoor environments for mobile robots by proposing the TOPS2 descriptor and THOR2 framework, achieving substantially higher accuracy than previous methods on real-world datasets like OCID and UW-IS Occluded.
Visual object recognition in unseen and cluttered indoor environments is a challenging problem for mobile robots. Toward this goal, we extend our previous work to propose the TOPS2 descriptor, and an accompanying recognition framework, THOR2, inspired by a human reasoning mechanism known as object unity. We interleave color embeddings obtained using the Mapper algorithm for topological soft clustering with the shape-based TOPS descriptor to obtain the TOPS2 descriptor. THOR2, trained using synthetic data, achieves substantially higher recognition accuracy than the shape-based THOR framework and outperforms RGB-D ViT on two real-world datasets: the benchmark OCID dataset and the UW-IS Occluded dataset. Therefore, THOR2 is a promising step toward achieving robust recognition in low-cost robots.