SpaceYOLO: A Human-Inspired Model for Real-time, On-board Spacecraft Feature Detection

The rapid proliferation of non-cooperative spacecraft and space debris in orbit has precipitated a surging demand for on-orbit servicing and space debris removal at a scale that only autonomous missions can address, but the prerequisite autonomous navigation and flightpath planning to safely capture an unknown, non-cooperative, tumbling space object is an open problem. Planning safe, effective trajectories requires real-time, automated spacecraft feature recognition algorithms to pinpoint the locations of collision hazards (e.g., solar panels or antennas) and safe docking features (e.g., satellite bodies or thrusters). Prior work in this area reveals that computer vision models' performance is highly dependent on the training dataset and its coverage of scenarios visually similar to the real scenarios that occur in deployment. Hence, the algorithm may have degraded performance under certain lighting conditions even when the rendezvous maneuver conditions of the chaser to the target spacecraft are the same. This work delves into how humans perform these tasks through a survey of how people experienced with spacecraft shapes and components recognize features of the three spacecraft: Landsat, Envisat, Anik, and the orbiter Mir. The survey reveals that the most common patterns in the human detection process were to consider the shape and texture of the features-antenna, solar panels, thrusters, and satellite bodies. This work introduces a novel algorithm called Space YOLO, which uses context-based decision processes, specifically shape and texture information, to perform object detection. Unlike traditional object detectors, the method demands far fewer labor hours for synthetic data preparation. Performance in autonomous spacecraft detection of SpaceYOLO is compared to ordinary YOLOv5 in hardware-in-the-loop experiments under different lighting and chaser maneuver conditions at the ORION facility at Florida Tech.