A Novel Network Architecture of Decision-Making for Self-Driving Vehicles Based on Long Short-Term Memory and Grasshopper Optimization Algorithm

Abstract

Long short-term memory network is one of the most important network architectures of decision-making for self-driving vehicles. Nevertheless, the decision-making accuracy of long short-term memory network is limited, the information of the surrounding vehicles is not taken into consideration, which is critical for the decision-making of the ego vehicle, and the classification capability of long shortterm memory network is poor. In this paper, a novel network architecture called improved long short-term memory network with support vector machine classifier optimized by grasshopper optimization algorithm (GOA-ImLSTM) is proposed. Three improvements are presented in GOA-ImLSTM. Firstly, to consider the information of the surrounding vehicles, a new network architecture, used to extract vital features for selfdriving vehicles, with three parallel long short-term memory network units and a network unit serial connected according to vehicle location is designed. Secondly, to improve classification accuracy, support vector machine with stronger classification capability than softmax is introduced to accomplish the classification task. Thirdly, to promote the classification capability of support vector machine, grasshopper optimization algorithm is employed to optimize the parameters of support vector machine. Moreover, to balance exploration and exploitation ability of grasshopper optimization algorithm, dynamic weights in position movement formula are defined. The experiments indicate that GOA-ImLSTM improves the accuracy of results compared with other decision-making methods for self-driving vehicles on the Next Generation SIMulation. INDEX TERMS grasshopper optimization algorithm, long short-term memory, self-driving decisionmaking, support vector machine.

Grasshopper Optimization Algorithm: Theory, Variants, and Applications

“…Another similar work was done by Barman et al [73] and Ibrahim et al [135]. Shi et al [136] suggested an improved long short-term memory GOA (GOA-ImLSTM) by hybridizing GOA with SVM and LSTM for decision-making for Self-Driving Vehicles. GOA-ImLSTM was assessed using Vehicle trajectory data collected from Roads of Los Angeles and California.…”

“…Content may change prior to final publication. [122] hybrid-GOA-GA [123] GOA-jDE [124] DE-GOA-KELM [125] HAGOA [126] GWGHA [127] BGOA [128] HGOA [129] SM-GNCSOA [130] GOALO [131] HAGOA [132] TLGOA [133] IWGOA [128] GOA-SVR [134] GOA-SVM [72] GOA-SVM [73] GOA-SVM [135] GOA-ImLSTM [136] GOA-MSVM [137] GOA-SVM [138] GOA was proposed by hybridizing GOA with GWO for tackling the text feature selection problem. GWO-GOA was assessed using eight datasets taking into account five metrics (i.e accuracy, sensitivity, specificity, precision, recall, and F-measure).…”

Research on Vehicle Active Steering Stability Control Based on Variable Time Domain Input and State Information Prediction

“…In order to avoid similar problems, LSTM as a specific RNN network model can solve the problem of a long-term dependence on historical information, so that based on directional selection and reasonable inheritance of current and historical information, it can complete information identification at the current time [33] and feature extraction [34] and information prediction at the next time [35] by comprehensively considering the role of historical input information. The main research content of this paper is based on the vehicle dynamic state information such as lateral acceleration, yaw rate, and tire force in the optimized time-domain length, and the LSTM network is adopted to extract the data features under the input state and predict the calculation to obtain the future sideslip angle of the center of mass.…”

A Novel Gated Recurrent Unit Network Based on SVM and Moth-Flame Optimization Algorithm for Behavior Decision-Making of Autonomous Vehicles

“…NGSIM does not contain vehicle steering angle information. Horizontal and vertical coordinates of three consecutive moments of the vehicle are used to calculate the steering angle [29]. The steering angle is calculated as follows.…”

“…Learning multiple sets of images through LSTM improved the accuracy of corner controlling. Shi et al [29] proposed a model of three parallel LSTM and one LSTM in series. The model extracted features by different lanes.…”