CNSv2: Probabilistic Correspondence Encoded Neural Image Servo
This work addresses a domain-specific problem for robotics and computer vision, offering an incremental improvement over previous neural control methods.
The paper tackles the problem of visual servo control failing in challenging scenarios like inconsistent illumination or textureless objects by proposing CNSv2, which uses probabilistic feature matching to improve robustness and achieve high precision in real-time, as validated through simulations and real-world experiments.
Visual servo based on traditional image matching methods often requires accurate keypoint correspondence for high precision control. However, keypoint detection or matching tends to fail in challenging scenarios with inconsistent illuminations or textureless objects, resulting significant performance degradation. Previous approaches, including our proposed Correspondence encoded Neural image Servo policy (CNS), attempted to alleviate these issues by integrating neural control strategies. While CNS shows certain improvement against error correspondence over conventional image-based controllers, it could not fully resolve the limitations arising from poor keypoint detection and matching. In this paper, we continue to address this problem and propose a new solution: Probabilistic Correspondence Encoded Neural Image Servo (CNSv2). CNSv2 leverages probabilistic feature matching to improve robustness in challenging scenarios. By redesigning the architecture to condition on multimodal feature matching, CNSv2 achieves high precision, improved robustness across diverse scenes and runs in real-time. We validate CNSv2 with simulations and real-world experiments, demonstrating its effectiveness in overcoming the limitations of detector-based methods in visual servo tasks.