MIXER: A Principled Framework for Multimodal, Multiway Data Association
This addresses a fundamental challenge in robotics for tasks like loop closure detection and object tracking, offering a novel integration of multimodal and multiway data association.
The paper tackles the problem of jointly matching objects across multiple, multimodal datasets in robotic perception, presenting a mixed-integer quadratic framework that achieves a 35% increase in F1 score compared to state-of-the-art methods.
A fundamental problem in robotic perception is matching identical objects or data, with applications such as loop closure detection, place recognition, object tracking, and map fusion. While the problem becomes considerably more challenging when matching should be done jointly across multiple, multimodal sets of data, the robustness and accuracy of matching in the presence of noise and outliers can be greatly improved in this setting. At present, multimodal techniques do not leverage multiway information, and multiway techniques do not incorporate different modalities, leading to inferior results. In contrast, we present a principled mixed-integer quadratic framework to address this issue. We use a novel continuous relaxation in a projected gradient descent algorithm that guarantees feasible solutions of the integer program are obtained efficiently. We demonstrate experimentally that correspondences obtained from our approach are more stable to noise and errors than state-of-the-art techniques. Tested on a robotics dataset, our algorithm resulted in a 35% increase in F1 score when compared to the best alternative.