A Full Transfer Learning LSTM-Based Fractional Order Optimization Method of GM(r,2) for Inferring Driving Intention

This paper proposes a fractional order optimization method of a fractional order multi-variable Grey model (GM(
$r$
,2)) based on a full transfer learning LSTM network. Firstly, a GM(
$r$
,2) was built with adhesion coefficient as input variable, namely, correlation factor sequence, and driving intention as output variable, namely, system behaviour characteristic sequence. Secondly, a long short-term memory (LSTM) network was trained by means of driving intention dataset, which is defined as source domain dataset. Adhesion coefficient, which is selected as test dataset, is defined as target domain dataset. By utilizing relative degree of grey incidence, it is proved that source domain dataset is extremely similar with target domain dataset. The LSTM network trained by driving intention dataset can be transferred fully to calculate optimization data. Finally, with the optimization data predicted by the LSTM network, an optimized fractional order of GM(
$r$
,2) can be calculated by fractional-order accumulation matrix calculation and least square fitting. Comparing with particle swarm optimization (PSO), the proposed optimization method can effectively improve the convergence of fractional order optimization values. The optimized GM(
$r_{opt}$
,2) was applied in inferring diving intention for an active safety driving system of electric vehicles. Simulation experiments are performed in car-following and lane-changing processes, respectively. The driving intention inferred by GM(
$r_{opt}$
,2) can change not only longitudinal safety distance, but also lane-changing trajectory with different road conditions. It can ensure vehicle driving safety. Experimental data can demonstrate that the proposed optimization method of fractional order is effective, and the optimized GM(
$r_{opt}$
,2) is appropriate to infer driving intention.