Real-time dynamic model learning and adaptation for Underwater Vehicles

Precision control of Unmanned Underwater Vehicles (UUVs) requires accurate knowledge of the dynamic characteristics of the vehicles. However, developing such models are time and resource intensive. The problem is further exacerbated by the sensitivity of the dynamic model to vehicle configuration. This is particularly true for hovering-class UUVs since sensor payloads are often mounted outside the vehicle body. This paper presents a method to learn a dynamic model for such a hovering-class UUV in real time from motion and position measurements. System identification techniques are employed to estimate equations of motion coefficients. Initial results on the approach are presented.