Neural Network On-Line Modeling for Mechanically Coupled Vehicle

This study was conducted to increase the usefulness of personal vehicles. Single-occupant personal vehicles are easy to handle, but their load capacities are smaller than other types of vehicles. This paper presents a solution to this problem in the form of a system for vehicles that couple mechanically. However, if vehicles are only coupled, their performance in braking, accelerating, and steering is degraded. The proposed system employs a neural network algorithm, constructs the whole coupled-vehicle model automatically while the vehicles are being driven, and makes drivers feel as if they are driving stand-alone vehicles. In this paper, we present the details of the proposed method and the results of computer simulation experiments that demonstrate the effectiveness of the system.