A knowledge-based agent was designed and validated to optimally re-distribute control authority in a torpedo-shaped autonomous underwater vehicle (AUV). The objective is greater fault tolerance in AUVs on long deployments when an AUV is unexpectedly underactuated from a jammed control fin. The optimization is achieved through a genetic algorithm that evaluates solutions based on a full non-linear analysis of the AUV dynamics and control. The agent is implemented on-board the AUV to provide timely reassignment of the fin control authority (gains) while underway so that the mission can continue or a potential vehicle loss be averted. The effectiveness of the agent is assessed through a parametric analysis that compares the response of the unexpectedly underactuated AUV with its initial gains against the optimized gains. The agent's greatest impact is in the event of a bow fin jam as the remaining functional planes maintain depth better with the agent's help. The ability to provide a timely and on-board optimal solution that adapts to a fin jam is a higher level of autonomy than has been previously reported.
展开▼