Deep Reinforcement Learning (DRL) is becoming a prominent method for autonomous driving due to its strong capability to generate complex driving policy. However, DRL motion planning still has limitations in safety performance including learning quality, convergence speed and the safety guarantee. To this end, this work proposes a safety-enhanced deep reinforcement learning method with dynamic safety guidance (DSG-DRL) for lane-change motion planning. It bears the following key features: 1) Able to learn a safer DRL driving policy by additionally including potentially unsafe behaviors; 2) Able to accelerate learning a safe policy by making dangerous driving experiences impressive; 3) Able to further enhance the driving safety by avoiding unexpected reckless action. The proposed DSG-DRL motion planner dares to make mistakes to learn the safe driving policy better and faster. By evaluating anticipated risk, it learns not only from the maneuvers right at the moments of collisions, but also from the dangerous maneuvers leading towards collisions. Besides, risk driving experiences are enhanced with additional memory batches and sampling prioritization. Moreover, reckless actions can be prevented by dynamic constraints both in training and testing, which further improves the safety performance. Simulation validation shows that the proposed method can learn a safer driving policy with faster convergence speed, achieving the high safety performance while keeping the driving efficiency.

Integrating the understanding and reasoning capabilities of Large Language Models (LLM) with the self-learning capabilities of Reinforcement Learning (RL) enables more reliable driving performance under complex driving conditions. There has been a lot of work exploring LLM-Dominated RL methods in the field of autonomous driving motion planning. These methods, which utilize LLM to directly generate policies or provide decisive instructions during policy learning of RL agent, are centrally characterized by an over-reliance on LLM outputs. However, LLM outputs are susceptible to hallucinations. Evaluations show that state-of-the-art LLM indicates a non-hallucination rate of only approximately 57.95\% when assessed on essential driving-related tasks. Thus, in these methods, hallucinations from the LLM can directly jeopardize the performance of driving policies. This paper argues that maintaining relative independence between the LLM and the RL is vital for solving the hallucinations problem. Consequently, this paper is devoted to propose a novel LLM-Hinted RL paradigm. The LLM is used to generate semantic hints for state augmentation and policy optimization to assist RL agent in motion planning, while the RL agent counteracts potential erroneous semantic indications through policy learning to achieve excellent driving performance. Based on this paradigm, we propose the HCRMP (LLM-Hinted Contextual Reinforcement Learning Motion Planner) architecture, which is designed that includes ①Augmented Semantic Representation Module to extend state space. ②Contextual Stability Anchor Module enhances the reliability of multi-critic weight hints by utilizing information from the knowledge base. ③Semantic Cache Module is employed to seamlessly integrate LLM low-frequency guidance with RL high-frequency control. Extensive experiments in CARLA validate HCRMP's strong overall driving performance. HCRMP achieves a task success rate of up to 80.3\% under diverse driving conditions with different traffic densities. Under safety-critical driving conditions, HCRMP significantly reduces the collision rate by 11.4\%, which effectively improves the driving performance in complex scenarios.

Lane-change is a common maneuver. However, completely egocentric lane-changing behavior may increase potential driving risks and cause oscillations in the movement of surrounding vehicles, referred to as disharmony. To improve the overall safety and efficiency of both ego vehicle and their surroundings, this paper proposes a convergent harmonious reinforcement learning (CHRL) approach to generate harmonious lane-changing strategies. It introduces a game-based model to measure the overall harmony cost. On this basis, a prosocial critic network is established to guide the policy toward harmony by decreasing the harmony cost. Meanwhile, CHRL identifies and penalizes discordant behaviors that may lead to high risk, accelerating the RL agent’s learning of harmonious driving strategies through expert demonstrations of the game model. Simulation and real-data tests validate that CHRL, compared to other lane-change methods and human drivers, improves the overall harmony of lane changes for autonomous vehicles.

In this paper, we propose a cloud control method with communication delay prediction for intelligent connected vehicles (ICVs), which not only constructs a prediction model using real-world 5G communication delay data, but also evaluate the effectiveness of the cloud control method considering delay in typical application scenarios. Firstly, for the application data interaction of 5G vehicle-to-network-to-vehicle (V2N2V) full-link, we collect a large amount of communication delay data through vehicle test. Then, a novel data-driven delay prediction method based on the Long Short-Term Memory (LSTM) network is introduced. Finally, a cloud control method considering communication delay is constructed at unsignalized intersection. The test results show that our method can not only achieve high delay prediction accuracy, but also significantly reduce vehicle velocity fluctuations and avoid collisions.

Autonomous driving requires efficient and safe decision making and motion planning in dynamic and uncertain environments. Future movement of surrounding vehicles is often difficult to represent. Besides, most existing studies consider decision making and planning/control separately. Both them may lead to the oscillation and unsafe for autonomous driving. This paper proposes an integrated framework of decision making and motion planning with oscillation-free capability. The proposed approach overcomes the shortcomings of autonomous driving for lane change/keeping maneuvers and is able to: i) make oscillation-free behavior decisions given biased prediction; ii) cut through in the traffic efficiently and safely when being in squeezed; iii) accelerate computation efficiency by building a state transfer model based on prediction uncertainty; iv) reduce the dissonance between decision-making and motion planning. A belief decision planner is designed with the uncertainty of the prediction trajectories. Lateral and longitudinal drivable corridors including the reference state and the related boundary constraints are built, which provide better suited information for planning to solve the optimal motion sequence more quickly and stably, and improve its consistency with decision module. Finally, the problem is formulated as an optimal control problem considering the vehicle dynamics and some soft constraints and the motion trajectory is solved by OSQP. Simulation and experimental tests are implemented to evaluate the feasibility and effectiveness of the proposed approach. Test results show that the integrated approach can make proper, safe and continuous decision and planning for autonomous vehicles and the calculation time is very low.

The tire-road peak adhesion coefficient (TRPAC) describes the tire adhesion limit that a road can provide. The TRPAC is a key parameter for precise vehicle motion control and an important basis for decision-making and planning of intelligent vehicles. Considering the critical and difficult problems in the estimation of TRPAC, such as slow convergence and low accuracy, a TRPAC estimation method based on the fusion of vehicle dynamics and machine vision is proposed in this paper. Based on the observability theory of nonlinear systems, local weak observability of the dynamics-based estimator is analyzed to explain the limitation of a single dynamics-based estimator. The framework of dynamics-image-based fusion estimator is then proposed, including the fusion of data, model and decision levels. A dynamics-based fusion estimator is designed by considering the coupling relationship of longitudinal and lateral tire forces to adapt the conditions of complex excitations. Start-and-stop strategy for the dynamics-based fusion estimator is designed by setting excitation thresholds for different types of road surfaces, which are identified using vision information. Parameter self-tuning for the dynamics-based fusion estimator based on the image-based estimator is proposed to improve convergence speed and reduce oscillation. The results of the simulation and vehicle test show that the road estimation error of the proposed method is within 0.03 and the convergence time is within 0.5 s. Compared with other existing estimators, the fusion estimator achieved better accuracy, sensitivity and stability, particularly when complex excitations were present.

Motion planning and vehicle prediction play an important role for autonomous vehicle, which aims to guarantee the driving safety under cut-in scenarios. This paper presents a hybrid prediction model for computing the future trajectory of the surrounding vehicles and a dynamic speed planner based on model predictive control to avoid collisions. Firstly, the hybrid prediction model combines the physics-based model and behavior-based model through Mamdani fuzzy logic. The predicted physic trajectory is computed using the constant yaw rate and velocity vehicle model. In addition, the prediction of driving intention is accomplished by using information of the difference between current motion and driving lanes. Furthermore, the predicted behavior trajectory is selected from the candidate quintic polynomial trajectory cluster through the designed cost function. Then, Gaussian propagation is applied at the fusion trajectory to compute the uncertainty distribution. Secondly, the dynamic speed planner based on model predictive control provides the optimal control command for the collision avoidance maneuver, which considers the future trajectory distribution of surrounding vehicles. Finally, the effectiveness of the proposed method is verified through simulation in different cut-in scenarios.

This paper proposes a road friction coefficient estimation method based on the fusion of machine vision and vehicle dynamics. A vehicle-mounted camera is used to obtain the front image. Based on the deep learning method, the road surface in the image is segmented and identified to obtain the road type. Besides, a road friction estimator with the tire longitudinal force estimation is designed. With the visual estimation results, a fusion estimation method is designed based on the structural parameter optimization. The results of simulation experiments show that the fusion estimator has the characteristics of fast convergence and high accuracy.

Anti-slip regulation (ASR) is one of the research focus in the field of active safety of electric vehicle. An ASR algorithm adaptive to road condition is proposed in this paper based on 4WD electric vehicle with in-wheel motors. The controller based on anti-windup sliding mode control is robust to wheel parameter uncertainty. The longitudinal velocity estimator based on the fusion of dynamics method and kinematics method is adopted to reduce the velocity estimation error. The road slope is estimated using recursive least square with forgetting factor and the longitudinal acceleration sensor information is calibrated by the road slope estimation for slope adaptive velocity estimation. At the same time, a road coefficient estimator is adopted to estimate road condition using improved Burckhardt model, so the optimal reference slip ratio is selected according to the estimated road adhesion coefficient for the maximum driving efficiency and the realization of adaptive anti-slip regulation. Multi-condition simulations show that the controller is adaptive to road changes, and it can suppress wheel slip ratio and ensure the vehicle stability.