Online Observability-Constrained Motion Suggestion via Efficient Motion Primitive-Based Observability Analysis

An active perception methodology is proposed to locally predict the observability condition in a reasonable horizon and suggest an observability-constrained motion direction for the next step to ensure an accurate and consistent state estimation performance of vision-based navigation systems. The methodology leverages an efficient EOG-based observability analysis and a motion primitive-based path sampling technique to realize the local observability prediction with a real-time performance. The observability conditions of potential motion trajectories are evaluated, and an informed motion direction is selected to ensure the observability efficiency for the state estimation system. The proposed approach is specialized to a representative optimization-based monocular vision-based state estimation formulation and demonstrated through simulation and experiments to evaluate the ability of estimation degradation prediction and efficacy of motion direction suggestion.