Satellite rendezvous maneuvers by means of computer vision

A two-dimensional satellite model plant is used to investigate automatic rendezvous and docking maneuvers with real image processing hardware in the loop. The three-dimensional shape of the passive docking partner is assumed to be known and is encoded in the knowledge base. Image processing is performed in real time and object recognition is achieved by feature aggregation exploiting the laws of perspective projection. During the approach and circumnavigation maneuvers, features are automatically tracked using dynamical models of the process for prediction, data filtering, and control. A sequential Kalman filter formulation is used to accommodate the time-varying length of the feature vector due to occlusion, failures, and redirection of processing elements by the knowledge base. A method has been developed to always select the feature vector yielding the best state estimate.