A Multilayer Perceptron Hazard Detector for Vision-Based Autonomous Planetary Landing

A hazard detection and target selection algorithm, based on Artificial Neural Networks, is presented. From a single frame acquired by a VIS camera, the system computes a hazard map, exploited to select the best target, in terms of safety, guidance constraints, and scientific interest. ANNs generalization properties allow the system to correctly operate also in conditions not explicitly considered during calibration. The net architecture design, training, verification and results are critically presented. Performances are assessed in terms of recognition accuracy and selected target safety. Results for different scenarios are discussed to highlight the effectiveness of the system.