Abstract: In order to overcome weak driver acceptability automated vehicles and improve system safety and adaptability on the real road, a human-machine hybrid decision-making strategy basing on the hybrid-augmented intelligence theory is proposed. The hybrid-augmented intelligence theory aims at dealing with the interaction issue between human and automated systems with “black and white box” property, and decouple their hybrid decision-making relationship. Basing on the driving authority allocation mechanism and human-machine decision-making knowledge base, the proposed strategy can be achieved and its advantages on decision-making of “1+1>2” between human and machine can be fully utilized as well. The driving authority allocation mechanism considering driving ability and human-machine trajectory similarity is established and the driving ability is classified and identified basing on the combination of subjective and objective methods and BP neural network. The decision-making logic of the automated vehicle subsystem is modeled basing on the LSTM network and its corresponding performance is evaluated. The comprehensive evaluation function consisting of the driving safety and comfort is proposed as the decision-making evaluation criterion for the shared control, and drivers’ acceptability is evaluated basing on subjective questionnaires. Using a high-precision intelligent driving simulation platform with human in the loop function for experimental data collection and system performance testing. The results show that when different levels of driver incentives are applied in the two lane and roundabout scenarios, the performance of the proposed human-machine hybrid decision-making strategy is better than that of the driver only, the full auto drive system and the shared control system based on the game framework.

Key words: vehicle engineering, shared control, human-machine hybrid decision-making, driving ability, hybrid-augmented intelligence