Feature extraction and dynamic identification of driving intention adapting to multi-mode emotions

Wang, Xiaoyuan; Liu, Yaqi; Xu, Qing; Xia, Yuanyuan; Zhao, Hongjin; Liu, Shijie; Han, Junyan

doi:10.1177/1687814019839906

Cited by 4 publications

(4 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The acceleration pedal opening is regarded as the input of the neural network, and the experimental results indicated that the identification accuracy is greater than 95% during the first 600 ms with the proposed model. Wang et al 7 presented a feature extraction and dynamic identification model based on rough set theory and backpropagation artificial neural network to recognize the driver's intentions. The experimental results indicated that the identification accuracies of acceleration, maintaining speed, and deceleration were 80.33%, 76.58%, and 70.36%, respectively.…”

Section: Research Progress Of Starting Intention Identificationmentioning

confidence: 99%

“…According to the dataset established above, the sample form is the multi-dimensional time-series sample, which is converted into a three-dimensional array and read by the input layer in the model, as expressed in equation ( 6). The input in each time step is the sequence sample at the time t of one starting sample, as shown in equation (7). The length of the required input time step is 15.…”

Section: Establishment Of Starting Intention Identification Model Bas...mentioning

confidence: 99%

See 1 more Smart Citation

Research on the identification of DCT vehicle driver’s starting intention based on LSTM neural network and multi-sensor data fusion

Liu

2022

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

Currently, the objective evaluation of the DCT vehicle drivability requires the accurate identification of the driver’s intention and vehicle state as well as the selection of the targeted evaluation indicators. The existing identification methods usually cannot divide the driver’s intentions in detail and make full use of the characteristics of time-series signals. Simultaneously, external kinematic sensors are more commonly used than the sensors of vehicle powertrain, which impacts the recognition effect. This paper proposes a new method for identifying the DCT vehicle driver’s starting intentions based on an LSTM neural network and multi-sensor data fusion. The DCT vehicle driver’s starting intentions are subdivided and defined based on human–vehicle interaction analysis and K-means clustering. The input of the model consists of 11-dimensional variables that include motion parameters of the vehicle collected by the external sensors and the powertrain parameters collected by onboard sensors. The method proposed in this paper first establishes a recognition window, which is utilized to extract the starting process samples from the DCT vehicle driving data. Second, the 11 variables of each sample are used as one set of multi-dimensional time-series signals, which are preprocessed through wavelet denoising. Finally, the LSTM network is used to identify the samples. The identification results indicate that the highest recognition accuracy of the proposed algorithm is 94.27%, which is approximately 5% higher than conventional methods, such as fully connected neural networks and support vector machines. Furthermore, the model with 11 input variables outperforms the model with fewer input variables. The effectiveness and superiority of the identification model have been demonstrated.

show abstract

Section: Research Progress Of Starting Intention Identificationmentioning

confidence: 99%

Section: Establishment Of Starting Intention Identification Model Bas...mentioning

confidence: 99%

Research on the identification of DCT vehicle driver’s starting intention based on LSTM neural network and multi-sensor data fusion

Liu

2022

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

show abstract

“…In order to reveal the influence of emotion on driving intention recognition, Xiao Yuan Wang obtained the multi-source dynamic data of human-vehicle-environment under the following conditions of different driving emotion states through emotion induction experiment and real vehicle experiment. The results showed that there were some differences in driving intention recognition under different emotion modes [4]. Klara Steinhauser and others conducted a driving simulator study.…”

Section: Introductionmentioning

confidence: 99%

Analysis of the dynamic influence of typical emotions on driving tendency

2020

jecet

View full text Add to dashboard Cite

This paper proposes a quantitative representation of driving tendency based on paired sample t-test and entropy, which is used to analyze the influence of anger, happiness, sadness and other driving emotions on dynamic driving tendency. By quantifying driving propensity, the dynamic changes of driving propensity under the influence of different emotions can be visualized. Randomly select the experimental personnel to carry out the simulation driving experiment. During the experiment, collect driving data of various driving states and human factors data of physiological indicators of drivers. A total of 84 effective experimental samples and 336 effective experimental data are obtained. The t-test of paired samples was used to analyze the differences of each index under different emotions. The characteristic parameters were selected to construct data matrix. The entropy value of each index was calculated by entropy and the driving tendency was quantitatively expressed according to the index weight. The driving tendency values of typical emotions and normal emotions were compared and analyzed, and the driving tendency transfer matrix was established to explore the driving tendency transfer law. The results show that the characteristics of driving propensity are different under different emotions. The three typical driving emotions have an impact on the dynamic change of driving propensity, and the most significant difference is the quantitative change of driving propensity under the influence of anger.

show abstract

“…Neural networks (NNs) are capable of learning the nonlinear characteristics inside a control object which is difficult to model in a deterministic manner. As such, NNs have been introduced to identify driving intentions in some special circumstances [22], [23]. In [24], the driver's starting intentions are defined as three modes, i.e., slow start, normal start and fast start, and the statistical law of the accelerator opening is set as the input of the back propagation NN (BPNN).…”

Section: Introductionmentioning

confidence: 99%

Driving Intention Identification Based on Long Short-Term Memory and A Case Study in Shifting Strategy Optimization

et al. 2019

View full text Add to dashboard Cite

Identification of driving intentions has increasingly attracted wide attention since it can be a valuable reference input of vehicle intelligent control systems. In this study, the long short-term memory (LSTM) is employed to identify the longitudinal intention online with high precision. To this end, the driving intentions when the vehicle runs on a straight and flat road are divided into five categories. The vehicle driving states such as the vehicle speed and acceleration are pre-processed to label the road test data. Subsequently, a LSTM classification model is established to identify the driving intention with inputs of opening degree of the accelerator pedal, vehicle speed and brake pedal force. Identification results reveal that the highest accuracy of the proposed algorithm attains 95.36%, which is around 20% higher than that of the traditional back propagation neural network. Finally, a driving intention-perceptive gear shifting strategy is developed with the help of the built recognition algorithm, and simulation results highlight that the strategy can effectively reduce the number of shifts and achieve better fuel economy.INDEX TERMS Driving intention, long short-term memory (LSTM), back propagation neural network (BPNN), dual clutch transmission (DCT), shift strategy, fuel economy.

show abstract

Feature extraction and dynamic identification of driving intention adapting to multi-mode emotions

Cited by 4 publications

References 45 publications

Research on the identification of DCT vehicle driver’s starting intention based on LSTM neural network and multi-sensor data fusion

Research on the identification of DCT vehicle driver’s starting intention based on LSTM neural network and multi-sensor data fusion

Analysis of the dynamic influence of typical emotions on driving tendency

Driving Intention Identification Based on Long Short-Term Memory and A Case Study in Shifting Strategy Optimization

Contact Info

Product

Resources

About