Search

Decision-making and motion planning are extremely important in autonomous driving to ensure safe driving in a real-world environment. This study proposes an online evolutionary decision-making and motion planning framework for autonomous driving based on a hybrid data- and model-driven method. First, a data-driven decision-making module based on deep reinforcement learning (DRL) is developed to pursue a rational driving performance as much as possible. Then, model predictive control (MPC) is employed to execute both longitudinal and lateral motion planning tasks. Multiple constraints are defined according to the vehicle’s physical limit to meet the driving task requirements. Finally, two principles of safety and rationality for the self-evolution of autonomous driving are proposed. A motion envelope is established and embedded into a rational exploration and exploitation scheme, which filters out unreasonable experiences by masking unsafe actions so as to collect high-quality training data for the DRL agent. Experiments with a high-fidelity vehicle model and MATLAB/Simulink co-simulation environment are conducted, and the results show that the proposed online-evolution framework is able to generate safer, more rational, and more efficient driving action in a real-world environment.

As the complexity of autonomous vehicles (AVs) continues to increase and artificial intelligence algorithms are becoming increasingly ubiquitous, a novel safety concern known as the safety of the intended functionality (SOTIF) has emerged, presenting significant challenges to the widespread deployment of AVs. SOTIF focuses on issues arising from the functional insufficiencies of the AVs’ intended functionality or its implementation, apart from conventional safety considerations. From the systems engineering standpoint, this study offers a comprehensive exploration of the SOTIF landscape by reviewing academic research, practical activities, challenges, and perspectives across the development, verification, validation, and operation phases. Academic research encompasses system-level SOTIF studies and algorithm-related SOTIF issues and solutions. Moreover, it encapsulates practical SOTIF activities undertaken by corporations, government entities, and academic institutions spanning international and Chinese contexts, focusing on the overarching methodologies and practices in different phases. Finally, the paper presents future challenges and outlook pertaining to the development, verification, validation, and operation phases, motivating stakeholders to address the remaining obstacles and challenges.

Abstract Environment perception is one of the most critical technology of intelligent transportation systems (ITS). Motion interaction between multiple vehicles in ITS makes it important to perform multi-object tracking (MOT). However, most existing MOT algorithms follow the tracking-by-detection framework, which separates detection and tracking into two independent segments and limit the global efficiency. Recently, a few algorithms have combined feature extraction into one network; however, the tracking portion continues to rely on data association, and requires complex post-processing for life cycle management. Those methods do not combine detection and tracking efficiently. This paper presents a novel network to realize joint multi-object detection and tracking in an end-to-end manner for ITS, named as global correlation network (GCNet). Unlike most object detection methods, GCNet introduces a global correlation layer for regression of absolute size and coordinates of bounding boxes, instead of offsetting predictions. The pipeline of detection and tracking in GCNet is conceptually simple, and does not require complicated tracking strategies such as non-maximum suppression and data association. GCNet was evaluated on a multi-vehicle tracking dataset, UA-DETRAC, demonstrating promising performance compared to state-of-the-art detectors and trackers.

Measurement(s) electroencephalogram measurement • driving behaviour measurement • face expression, body gesture and road scenario measurement • emotion and persionality Technology Type(s) electroencephalography (EEG) • driving simulator • visual observation method • self-reported scale

Abstract The cooperation between an autonomous vehicle and a nearby vehicle is critical to ensure driving safety in the lane-exchanging scenario. The nearby vehicle trajectory needs to be predicted, from which the autonomous vehicle is controlled to prevent possible collisions. This paper proposes a lane-exchanging driving strategy for the autonomous vehicle to cooperate with the nearby vehicle by integrating vehicle trajectory prediction and motion control. A trajectory prediction method is developed to anticipate the nearby vehicle trajectory. The Gaussian mixture model (GMM), together with the vehicle kinematic model, are synthesized to predict the nearby vehicle trajectory. A potential-field-based model predictive control (MPC) approach is utilized by the autonomous vehicle to conduct the lane-exchanging maneuver. The potential field of the nearby vehicle is considered in the controller design for collision avoidance. On-road driving data verification shows that the nearby vehicle trajectory can be predicted by the proposed method. CarSim® simulations validate that the autonomous vehicle can perform the lane-exchanging maneuver and avoid the nearby vehicle using the proposed driving strategy. The autonomous vehicle can thus safely perform the lane-exchanging maneuver and avoid the nearby vehicle.

Abstract There is an increasing awareness of the need to reduce traffic accidents and fatality due to vehicle collision. Post-impact hazards can be more serious as the driver may fail to maintain effective control after collisions. To avoid subsequent crash events and to stabilize the vehicle, this paper proposes a post-impact motion planning and stability control method for autonomous vehicles. An enabling motion planning method is proposed for post-impact situations by combining the polynomial curve and artificial potential field while considering obstacle avoidance. A hierarchical controller that consists of an upper and a lower controller is then developed to track the planned motion. In the upper controller, a time-varying linear quadratic regulator is presented to calculate the desired generalized forces. In the lower controller, a nonlinear-optimization-based torque allocation algorithm is proposed to optimally coordinate the actuators to realize the desired generalized forces. The proposed scheme is verified under comprehensive driving scenarios through hardware-in-loop tests.

Abstract Planning and decision-making technology at intersections is a comprehensive research problem in intelligent transportation systems due to the uncertainties caused by a variety of traffic participants. As wireless communication advances, vehicle infrastructure integrated algorithms designed for intersection planning and decision-making have received increasing attention. In this paper, the recent studies on the planning and decision-making technologies at intersections are primarily overviewed. The general planning and decision-making approaches are presented, which include graph-based approach, prediction base approach, optimization-based approach and machine learning based approach. Since connected autonomous vehicles (CAVs) is the future direction for the automated driving area, we summarized the evolving planning and decision-making methods based on vehicle infrastructure cooperative technologies. Both four-way signalized and unsignalized intersection(s) are investigated under purely automated driving traffic and mixed traffic. The study benefit from current strategies, protocols, and simulation tools to help researchers identify the presented approaches’ challenges and determine the research gaps, and several remaining possible research problems that need to be solved in the future.

Abstract To reduce the discrepancy between the source and target domains, a new multi-label adaptation network (ML-ANet) based on multiple kernel variants with maximum mean discrepancies is proposed in this paper. The hidden representations of the task-specific layers in ML-ANet are embedded in the reproducing kernel Hilbert space (RKHS) so that the mean-embeddings of specific features in different domains could be precisely matched. Multiple kernel functions are used to improve feature distribution efficiency for explicit mean embedding matching, which can further reduce domain discrepancy. Adverse weather and cross-camera adaptation examinations are conducted to verify the effectiveness of our proposed ML-ANet. The results show that our proposed ML-ANet achieves higher accuracies than the compared state-of-the-art methods for multi-label image classification in both the adverse weather adaptation and cross-camera adaptation experiments. These results indicate that ML-ANet can alleviate the reliance on fully labeled training data and improve the accuracy of multi-label image classification in various domain shift scenarios.

Abstract This paper investigates the formation control of connected autonomous vehicle (CAV) platoons moving in multi lanes using distance‐based formation control techniques based on rigid graphs and V2V communication. A hierarchical architecture is proposed to decompose the cooperative control into velocity planning and vehicle dynamic control. A new velocity planning method is first developed via a distributed distance‐based formation controller so that each vehicle can keep platoon and change lane. Then, for the vehicle dynamics with nonlinearities and bounded disturbances, an adaptive controller is designed for regulating driving/braking torque to achieve the longitudinal velocity output of the velocity planner. The steering controller is designed to adjust the yaw angle of each vehicle to track and change lanes. Furthermore, stability analysis is conducted based on the Lyapunov theory. Finally, the applications of the proposed control designs to various of automated highway system (AHS) scenarios including lane‐change, curve lane and platoon overtaking, are simulated and numerically analysed to validate the effectiveness of theoretical results.

The traffic situation at an urban intersection is complicated, due to the numerous internal conflicts and all kinds of traffic accidents. With the objective of improving road safety, the automotive industry is moving toward intelligent vehicles. The major challenges are accurately perceiving the road traffic environment, detecting the potential traffic conflicts, and proposing the alternative driving strategies. This paper summarizes the existing researches on traffic conflicts from the perspective of intelligent vehicles. The intelligent vehicles can perceive the surrounding environment, extract road condition information, and detect obstacles for avoiding collisions or mitigating accidents. It expounds that the perception technology of intelligent vehicles can be divided into three main categories, namely, the perception technology, the communication technology, and the fusion of perception-communication technology. At the same time, the existing technical problems are analyzed. Finally, future development trends in this field are discussed.

Autonomous driving is a promising technology to reduce traffic accidents and improve driving efficiency. In this work, a deep reinforcement learning (DRL)-enabled decision-making policy is constructed for autonomous vehicles to address the overtaking behaviors on the highway. First, a highway driving environment is founded, wherein the ego vehicle aims to pass through the surrounding vehicles with an efficient and safe maneuver. A hierarchical control framework is presented to control these vehicles, which indicates the upper-level manages the driving decisions, and the lower-level cares about the supervision of vehicle speed and acceleration. Then, the particular DRL method named dueling deep Q-network (DDQN) algorithm is applied to derive the highway decision-making strategy. The exhaustive calculative procedures of deep Q-network and DDQN algorithms are discussed and compared. Finally, a series of estimation simulation experiments are conducted to evaluate the effectiveness of the proposed highway decision-making policy. The advantages of the proposed framework in convergence rate and control performance are illuminated. Simulation results reveal that the DDQN-based overtaking policy could accomplish highway driving tasks efficiently and safely.

An adaptive potential field is designed to adapt the acceleration/deceleration and mass of the obstacle. The potential fields are established in a transformed road coordinate system to improve the feasibility and robustness. A path planning method is proposed based on the designed adaptive potential field to improve the driving safety and the ride comfort of autonomous vehicles in complex driving scenarios, which including the cut-in, emergency braking, obstacle sudden accelerating during overtaking and the curve road driving scenarios. The effectiveness of the proposed method is validated by simulations with constructed and real data, respectively. The $TTC\text{s}$ (Time-to-Collision) and the maximum lateral accelerations are used to evaluate the improvements on safety and ride comfort. The results show that both the driving safety and ride comfort are efficiently improved by using the proposed approach in emergency braking and accelerating scenarios. Meanwhile, the proposed method can be well applied in a curve road driving environment.

Prior to realizing fully autonomous driving, human intervention is periodically required to guarantee vehicle safety. This poses a new challenge in human–machine interaction, particularly during the control authority transition from automated functionality to a human driver. Herein, this challenge is addressed by proposing an intelligent haptic interface based on a newly developed two‐phase human–machine interaction model. The intelligent haptic torque is applied to the steering wheel and switches its functionality between predictive guidance and haptic assistance according to the varying state and control ability of human drivers. This helps drivers gradually resume manual control during takeover. The developed approach is validated by conducting vehicle experiments with 26 participants. The results suggest that the proposed method effectively enhances the driving state recovery and control performance of human drivers during takeover compared with an existing approach. Thus, this new method further improves the safety and smoothness of human–machine interaction in automated vehicles.

Summary: In this work, pattern recognition and characterization of the neuromuscular dynamics of driver upper limb during naturalistic driving were studied. During the human-in-the-loop experiments, two steering tasks, namely, the passive and active steering tasks, were instructed to be completed by the subjects. Furthermore, subjects manipulated the steering wheel with two distinct postures and six different hand positions. The neuromuscular dynamics of subjects' upper limb were measured using electromyogram signals, and the behavioral data, including the steering torque and steering angle, were also collected. Based on the experimental data, patterns of muscle activities during naturalistic driving were investigated. The correlations, amplitudes, and responsiveness of the electromyogram signals, as well as the smoothness and regularity of the steering torque were discussed. The results reveal the mechanisms of neuromuscular dynamics of driver upper limb and provide a theoretical foundation for the design of the future human-machine interface for automated vehicles.

This paper proposes a framework for uncertainty prediction in complex fusion networks, where signals become available sporadically. Assuming there is no information of the sensor characteristics available, a surrogated model of the sensor uncertainty is yielded directly from data through artificial neural networks. The strategy developed is applied to autonomous vehicle localization through odometry sensors (speed and orientation), so as to determine the location uncertainty in the trajectory. The results obtained allow for fusion of autonomous vehicle location measurements, and effective correction of the accumulated odometry error in most scenarios. The neural networks applicability and generalization capacity are proven, evidencing the suitability of the presented methodology for uncertainty estimation in non-linear and intractable processes.

The traditional potential field-based path planning is likely to generate unexpected path by strictly following the minimum potential field, especially in the driving scenarios with multiple obstacles closely distributed. A hybrid path planning is proposed to avoid the unsatisfying path generation and to improve the performance of autonomous driving by combining the potential field with the sigmoid curve. The repulsive and attractive potential fields are redesigned by considering the safety and the feasibility. Based on the objective of the shortest path generation, the optimized trajectory is obtained to improve the vehicle stability and driving safety by considering the constraints of collision avoidance and vehicle dynamics. The effectiveness is examined by simulations in multiobstacle dynamic and static scenarios. The simulation results indicate that the proposed method shows better performance on vehicle stability and ride comfortability than that of the traditional potential field-based method in all the examined scenarios during the autonomous driving.

The authors wish to make the following corrections to this paper [...]

As the main component of an autonomous driving system, the motion planner plays an essential role for safe and efficient driving. However, traditional motion planners cannot make full use of the on-board sensing information and lack the ability to efficiently adapt to different driving scenes and behaviors of different drivers. To overcome this limitation, a personalized behavior learning system (PBLS) is proposed in this paper to improve the performance of the traditional motion planner. This system is based on the neural reinforcement learning (NRL) technique, which can learn from human drivers online based on the on-board sensing information and realize human-like longitudinal speed control (LSC) through the learning from demonstration (LFD) paradigm. Under the LFD framework, the desired speed of human drivers can be learned by PBLS and converted to the low-level control commands by a proportion integration differentiation (PID) controller. Experiments using driving simulator and real driving data show that PBLS can adapt to different drivers by reproducing their driving behaviors for LSC in different scenes. Moreover, through a comparative experiment with the traditional adaptive cruise control (ACC) system, the proposed PBLS demonstrates a superior performance in maintaining driving comfort and smoothness.

Although at present legislation does not allow drivers in a Level 3 autonomous vehicle to engage in a secondary task, there may become a time when it does. Monitoring the behaviour of drivers engaging in various non-driving activities (NDAs) is crucial to decide how well the driver will be able to take over control of the vehicle. One limitation of the commonly used face-based head tracking system, using cameras, is that sufficient features of the face must be visible, which limits the detectable angle of head movement and thereby measurable NDAs, unless multiple cameras are used. This paper proposes a novel orientation sensor based head tracking system that includes twin devices, one of which measures the movement of the vehicle while the other measures the absolute movement of the head. Measurement error in the shaking and nodding axes were less than 0.4°, while error in the rolling axis was less than 2°. Comparison with a camera-based system, through in-house tests and on-road tests, showed that the main advantage of the proposed system is the ability to detect angles larger than 20° in the shaking and nodding axes. Finally, a case study demonstrated that the measurement of the shaking and nodding angles, produced from the proposed system, can effectively characterise the drivers’ behaviour while engaged in the NDAs of chatting to a passenger and playing on a smartphone.