Qinyu Sun

The human-vehicle collaboration in automated vehicles is an effective transitional means to overcome the difficulty of rapidly transitioning to a highly automated level of intelligence. Furthermore, it can fully leverage the strengths of both drivers and autonomous driving systems, embodying a design philosophy of human-centered. Therefore, this paper provides a review and perspectives of the human-vehicle collaboration for automated vehicles. First, the concept, forms and methods of human-vehicle collaboration are reviewed. Then, a human-vehicle mutual trust collaboration framework based on complementary advantages of humans and vehicles and brain-like intelligence is proposed. Specifically, the framework focuses on driver behavior understanding and brain-like cognitive decision planning. After that, the methods of driver behavior understanding and brain-like cognitive decision planning are summarized. Finally, challenges and future works are analyzed to contribute the develop of understandable, trustable, and acceptable human-vehicle collaboration systems.

The electronic differential control (EDC) system is an indispensable key technology for distributed-drive buses. However, compared to traditional buses with mechanical differentials, distributed-drive buses based on EDC have more severe tire wear and tire bias wear. To tackle these problems, we consider the reduction of tire wear, and propose an EDC strategy based on model predictive control (MPC) to improve the steering stability and extend the tire service life. First, nonlinear three-degree-of-freedom dynamics model and magic tire formula are established. Second, the slip ratio is selected as the observation of tire wear, and the underlying causes of tire wear are analyzed via simulation tests under different driving conditions. Third, a three-layer EDC strategy is designed. The upper layer is the EDC trigger condition and vehicle speed-following control; the middle layer is the calculation of control parameters such as the desired stability parameters, estimated sideslip angle, and slip state of the driving wheels; and the lower layer is the MPC-based driving torque controller to obtain the motor torque. Finally, the proposed MPC-based EDC strategy is validated and compared by simulation tests and real experiments. The comparative results demonstrate that the MPC-based EDC can achieve optimized differential torque control to effectively reduce the tire wear while improving the stability in different steering maneuvers.

Real-time driver behavior detection (DBD) is essential for developing driver-centered human-vehicle co-driving systems. This paper proposes an accurate and easily implementable DBD method based on driver behavior images and deep learning. Convolutional neural networks have difficulty dealing with changes in driver behavior images (rotation, scale, and translation). They suffer from a tradeoff between accuracy and number of trainable parameters, noise interference in images of driver behavior, and the black-box problem of neural networks, limiting the effectiveness of current DBD methods. Therefore, we design a novel deep learning-based DBD method consisting of a deep deformable inverted residual network with an attention mechanism. Deformable convolution is used to deal with image rotation and translation. An inverted residual block and linear bottleneck approach based on depthwise separable convolution is used to reduce the number of trainable parameters while maintaining high accuracy. An attention mechanism based on soft thresholding is incorporated into the nonlinear transformation layers to extract driver behavior-relevant features. We also innovatively propose a visualization method to improve the interpretability of the proposed method. The experimental results show that the proposed method can accurately detect driver behavior (95.17% mAP on the Kaggle driving test dataset), significantly outperforming state-of-the-art methods regarding accuracy, real-time performance, and reliability.

Driving simulators have been widely used in driving behavior analysis and intelligent driving algorithm development. However, the validity of driving behavior data derived from driving simulators remains unclear. In this study, 30 Chinese drivers were recruited to participate in two experiments: on-road and simulator experiments. An instrumented vehicle and a high-fidelity simulator were used in the on-road and simulator experiments, respectively, to investigate the effects of high speed (60, 80, and 100 km/h) and a visual distraction task on the lateral driving performance, including lane deviation (LD), standard deviation of the lane position (SDLP) rate, standard deviation of the steering wheel angle (SDSWA) rate, and steering wheel reversal rates (SRRs) (at levels of 1.3° and 2.5°). It was found that the visual distraction task impaired the drivers' lane-keeping ability. Furthermore, the driving task had similar effects on the LD, SDLP rate, and SRRs (2.5°) in the on-road and simulator experiments. The effects of the driving speed on the LD, SDLP rate, and SDSWA rate were comparable in both driving environments. However, the results confirmed that even a high-fidelity driving simulator could not achieve perfect absolute validity. The results provided preliminary evidence that the high-fidelity driving simulator used in this study might be an effective tool for investigating the effects of visual distractions task on lateral driving behavior.

Developing a human-like autonomous driving system has gained increasing amounts of attention from both technology companies and academic institutions, as it can improve the interpretability and acceptance of the autonomous system. Planning a safe and human-like obstacle avoidance trajectory is one of the critical issues for the development of autonomous vehicles (AVs). However, when designing automatic obstacle avoidance systems, few studies have focused on the obstacle avoidance characteristics of human drivers. This paper aims to develop an obstacle avoidance trajectory planning and trajectory tracking model for AVs that is consistent with the characteristics of human drivers’ obstacle avoidance trajectory. Therefore, a modified artificial potential field (APF) model was established by adding a road boundary repulsive potential field and ameliorating the obstacle repulsive potential field based on the traditional APF model. The model predictive control (MPC) algorithm was combined with the APF model to make the planning model satisfy the kinematic constraints of the vehicle. In addition, a human driver’s obstacle avoidance experiment was implemented based on a six-degree-of-freedom driving simulator equipped with multiple sensors to obtain the drivers’ operation characteristics and provide a basis for parameter confirmation of the planning model. Then, a linear time-varying MPC algorithm was employed to construct the trajectory tracking model. Finally, a co-simulation model based on CarSim/Simulink was established for off-line simulation testing, and the results indicated that the proposed trajectory planning controller and the trajectory tracking controller were more human-like under the premise of ensuring the safety and comfort of the obstacle avoidance operation, providing a foundation for the development of AVs.

The accurate and prompt recognition of a driver’s cognitive distraction state is of great significance to intelligent driving systems (IDSs) and human-autonomous collaboration systems (HACSs). Once the driver’s distraction status has been accurately identified, the IDS or HACS can actively intervene or take control of the vehicle, thereby avoiding the safety hazards caused by distracted driving. However, few studies have considered the time–frequency characteristics of the driving behavior and vehicle status during distracted driving for the establishment of a recognition model. This study seeks to exploit a recognition model of cognitive distraction driving according to the time–frequency analysis of the characteristic parameters. Therefore, an on-road experiment was implemented to measure the relative parameters under both normal and distracted driving via a test vehicle equipped with multiple sensors. Wavelet packet analysis was used to extract the time–frequency characteristics, and 21 pivotal features were determined as the input of the training model. Finally, a bidirectional long short-term memory network (Bi-LSTM) combined with an attention mechanism (Atten-BiLSTM) was proposed and trained. The results indicate that, compared with the support vector machine (SVM) model and the long short-term memory network (LSTM) model, the proposed model achieved the highest recognition accuracy (90.64%) for cognitive distraction under the time window setting of 5 s. The determination of time–frequency characteristic parameters and the more accurate recognition of cognitive distraction driving achieved in this work provide a foundation for human-centered intelligent vehicles.

Determining an appropriate time to execute a lane change is a critical issue for the development of Autonomous Vehicles (AVs).However, few studies have considered the rear and the front vehicle-driver’s risk perception while developing a human-like lane-change decision model. This paper aims to develop a lane-change decision model for AVs and to identify a two level threshold that conforms to a driver’s perception of the ability to safely change lanes with a rear vehicle approaching fast. Based on the signal detection theory and extreme moment trials on a real highway, two thresholds of safe lane change were determined with consideration of risk perception of the rear and the subject vehicle drivers, respectively. The rear vehicle’s Minimum Safe Deceleration (MSD) during the lane change maneuver of the subject vehicle was selected as the lane change safety indicator, and was calculated using the proposed human-like lane-change decision model. The results showed that, compared with the driver in the front extreme moment trial, the driver in the rear extreme moment trial is more conservative during the lane change process. To meet the safety expectations of the subject and rear vehicle drivers, the primary and secondary safe thresholds were determined to be 0.85 m/s² and 1.76 m/s², respectively. The decision model can help make AVs safer and more polite during lane changes, as it not only improves acceptance of the intelligent driving system, but also further ensures the rear vehicle’s driver’s safety.

Accurate identification of pedestrian crossing intention is of great significance to the safe and efficient driving of future fully automated vehicles in the city. This paper focuses on pedestrian intention recognition on the basis of pedestrian detection and tracking. A large number of natural crossing sequence data of pedestrians and vehicles are first collected by a laser scanner and HD camera, then 1980 effective crossing samples of pedestrians are selected. Influencing parameter sets of pedestrian crossing intention are then obtained through statistical analysis. Finally, long short-term memory network with attention mechanism (AT-LSTM) model is proposed. Compared with the support vector machine (SVM) model, results show that when the pedestrian crossing intention is recognized 0 s prior to crossing, the recognition accuracy of the AT-LSTM model for pedestrian crossing intention is 96.15%, which is 6.07% higher than that of SVM model; when the pedestrian crossing intention is recognized 0.6 s prior, the recognition accuracy of AT-LSTM model is 90.68%, which is 4.85% higher than that of the SVM model. The determination of pedestrian crossing intention parameter set and the more accurate recognition of pedestrian intention provided in this work provide a foundation for future fully automated driving vehicles.

The frequent false alarms in Forward Collision Warning systems not only disturb the normal operation of drivers, but also reduce the user acceptance of the warning systems. However, drivers with disparate driving characteristics possess different safety cognition of car-following braking behavior; systems with stationary warning thresholds inevitably lead to higher false positive and false negative rates for aggressive and conservative drivers, respectively. In this study, we proposed an adaptive algorithm that learns the characteristics of individual drivers during car-following braking processes, and determined the optimal threshold online to adapt to different drivers. Signal detection theory was employed and the results of the accuracy, false negative rate, and false positive rate were used to capture drivers’ characteristics of car-following braking behavior. The optimal warning thresholds were continuously selected online during the learning stage based on changes in the drivers’ characteristics. The developed algorithm by conducting actual vehicle tests with two participants were evaluated. The offline statistical analysis results of the participants’ car-following braking characteristics were compared with the online results of the warning threshold adjustments from the adaptive algorithm. The comparison results indicated that the adaptive algorithm could effectively capture the drivers’ car-following braking characteristics and determine an appropriate warning threshold.