Hybrid Vision Servoing with Depp Alignment and GRU-Based Occlusion Recovery

Traditional robotic controllers have long relied on proprioceptive sensors such as joint encoders, inertial measurement units, and force - torque sensors to estimate position and motion, but these often suffer from drift, calibration errors, and limited environmental awareness [1]. Image - based visual servoing has therefore been widely adopted for high - precision robotic assembly, aerial vehicle stabilization, and minimally invasive surgery, where direct visual feedback can compensate for model uncertainties an d encoder inaccuracies [2] [3]. In these closed - loop systems, perception must deliver sub - pixel localization accuracy at control rates above 30 Hz while tolerating partial or full occlusions, illumination shifts, and motion blur to maintain loop stability and precision [4]. Even millimeter - level tracking errors can accumulate into significant actuation drift, undermining safety and performance into sub - millimeter surgical targeting or centimeter - scale drone landing [5] [6]. Early IBVS methods emerged in the early 1990s to simplify robot control by directly mapping image features to velocity commands, establishing the foundation for image - space loop closure [2]. Handcrafted detectors such as SIFT [7], which identifies scale - invariant keypoints, SURF [8], which accelerates detection using integral images, and ORB [9], which offers an efficient binary alternative, were paired with RANSASC [10] to filter out mismatches. However, these sparse approaches struggled when keypoints wer e lost to occlusion or blur. To achieve denser alignment, the Lucas - Kanade algorithm was introduced to iteratively minimize photometric error over image patches and enable smooth sub - pixel registration [11].