A Neuromorphic Vision-Based Measurement for Robust Relative Localization in Future Space Exploration Missions

Space exploration has witnessed revolutionary changes upon landing of the Perseverance Rover on Martian surface and demonstrating first flight beyond Earth by Mars helicopter, Ingenuity. During their mission Mars, Ingenuity collaboratively explore surface, where scouts terrain information for rover’s safe traversability. Hence, determining relative poses between both platforms is paramount importance success this mission. Driven necessity, work proposes a robust localization system based fusion neuromorphic vision-based measurements (NVBMs) inertial measurements. The emergence vision triggered paradigm shift in computer community, due to its unique working principle delineated with asynchronous events variations light intensities occurring scene. This implies that observations cannot be acquired static scenes illumination invariance. To circumvent limitation, high frequency active landmarks are inserted scene guarantee consistent event firing. These adopted as salient features facilitate localization. A novel event-based landmark identification algorithm using Gaussian Mixture Models (GMM) developed matching correspondences formulating our NVBMs. NVBMs fused proposed state estimators, tracking Kalman filter (LTKF) translation decoupled (TDKF) localization, respectively. was tested variety experiments outperformed state-of-the-art approaches accuracy range.