In this paper, an improved method for estimating the state of charge (SOC) of lithium-ion batteries is proposed, which is developed from the particle filter (PF). An improved genetic particle filter (GPF), owing to the advantages of the PF and genetic algorithm, is proposed to overcome the disadvantage of the traditional particle filter: lacking the diversity of particles. Firstly, the relationship between SOC and open-circuit voltage (OCV) is identified on the low-current OCV test. Secondly, a first-order resistor and capacitance (RC) model is established, then, the least-squares algorithm is used to identify the model parameters via the incremental current test. Thirdly, GPF and the improved GPF (IGPF) are proposed to solve the problems of the PF. The method based on the IGPF is proposed to estimate the state of power (SOP). Finally, IGPF, GPF, and PF are employed to estimate the SOC on the federal urban driving schedule (FUDS). The results show that compared with traditional PF, the errors of the IGPF are 20% lower, and compared with GPF, the maximum error of the IGPF has declined 1.6% SOC. The SOC that is estimated by the IGPF is applied to estimate the SOP for battery, considering the restrictions from the peak SOC, the voltage, and the instruction manual. The result shows that the method based on the IGPF can successfully estimate SOP.

Robust and quick road curb detection under various situations is critical in developing intelligent vehicles. However, the road curb detection is easily affected by the obstacles in the road area when Lidar based method is applied. A practical road curb detection method using point cloud from a three-dimensional Lidar for autonomous vehicle is reported in this paper. First, a multi-feature, loose-threshold, varied-scope ground segmentation method is presented to increase the robustness of ground segmentation with which obstacles above the ground can be detected. Second, the road curb is detected by applying the global road trend and an extraction-update mechanism. Experiments show the robustness and efficiency of the road curb detection under various environments. The road curb detection method is 10 times the speed of traditional method and the accuracy is much higher than existing methods.

The autonomous vehicle consists of perception, decision-making, and control system. The study of path planning method has always been a core and difficult problem, especially in complex environment, due to the effect of dynamic environment, the safety, smoothness, and real-time requirement, and the nonholonomic constraints of vehicle. To address the problem of travelling in complex environments which consists of lots of obstacles, a two-layered path planning model is presented in this paper. This method includes a high-level model that produces a rough path and a low-level model that provides precise navigation. In the high-level model, the improved Bidirectional Rapidly-exploring Random Tree (Bi-RRT) based on the steering constraint is used to generate an obstacle-free path while satisfying the nonholonomic constraints of vehicle. In low-level model, a Vector Field Histogram- (VFH-) guided polynomial planning algorithm in Frenet coordinates is introduced. Based on the result of VFH, the aim point chosen from improved Bi-RRT path is moved to the most suitable location on the basis of evaluation function. By applying quintic polynomial in Frenet coordinates, a real-time local path that is safe and smooth is generated based on the improved Bi-RRT path. To verify the effectiveness of the proposed planning model, the real autonomous vehicle has been placed in several driving scenarios with different amounts of obstacles. The two-layered real-time planning model produces flexible, smooth, and safe paths that enable the vehicle to travel in complex environment.

This study presents the first investigation into the problem of autonomous vehicle (AV) merging into existing platoons, proposing a multi-agent deep reinforcement learning (MA-DRL)-based cooperative control framework. The developed MA-DRL architecture enables coordinated learning among multiple autonomous agents to address the multi-objective coordination challenge through synchronized control of platoon longitudinal acceleration, AV steering and acceleration. To enhance training efficiency, we develop a dual-layer multi-agent maximum Q-value proximal policy optimization (MAMQPPO) method, which extends the multi-agent PPO algorithm (a policy gradient method ensuring stable policy updates) by incorporating maximum Q-value action selection for platoon gap control and discrete command generation. This method simplifies the training process by using maximum Q-value action policy optimization to learn platoon gap selection and discrete action commands. Furthermore, a partially decoupled reward function (PD-Reward) is designed to properly guide the behavioral actions of both AVs and platoons while accelerating network convergence. Comprehensive highway simulation experiments show the proposed method reduces merging time by 37.69% (12.4 s vs. 19.9 s) and energy consumption by 58% (3.56 kWh vs. 8.47 kWh) compared to existing methods (the quintic polynomial-based + PID (Proportional–Integral–Differential)).

With the development of autonomous driving technology, truck platooning control has become a reality. Truck platooning can improve road capacity by maintaining a minor headway. Platooning systems can significantly reduce fuel consumption and emissions, especially for trucks. In this study, we designed a Platoon-MAPPO algorithm to implement truck platooning control based on multi-agent reinforcement learning for a platooning facing an on-ramp scenario on highway. A centralized training, decentralized execution algorithm was used in this paper. Each truck only computes its actions, avoiding the data computation delay problem caused by centralized computation. Each truck considers the truck status in front of and behind itself, maximizing the overall gain of the platooning and improving the global operational efficiency. In terms of performance evaluation, we used the traditional rule-based platooning following model as a benchmark. To ensure fairness, the model used the same network structure and traffic scenario as our proposed model. The simulation results show that the algorithm proposed in this paper has good performance and improves the overall efficiency of the platoon while guaranteeing traffic safety. The average energy consumption decreased by 14.8%, and the road occupancy rate decreased by 43.3%.

Purpose: Navigating in off-road environments is a huge challenge for autonomous vehicles, due to the safety requirement, the effects of noises and non-holonomic constraints of vehicle. This paper aims to describe a path planning method based on fuzzy support vector machine (FSVM) and general regression neural network (GRNN) that is able to provide a solution path for the autonomous vehicle navigating in the off-road environments. Design/methodology/approach: The authors decompose the path planning problem into three steps. In the first step, A* algorithm is applied to obtain the positive and negative samples. In the second step, the authors use a learning approach based on radial basis function kernel FSVM to maximize the safety margin for driving, and the fuzzy membership is designed based on GRNN which can help to resolve the problem that the traditional path planning method is easily influenced by noises or outliers. In the third step, the Bezier interpolation algorithm is used to smooth the path. The simulations are designed to verify the parameters of the path planning algorithm. Findings: The method is implemented on autonomous vehicle and verified against many outdoor scenes. Road test indicates that the proposed method can produce a flexible, smooth and safe path with good anti-jamming performance. Originality/value: This paper applied a new path planning method based on GRNN-FSVM for autonomous vehicle navigating in off-road environments. GRNN-FSVM can reduce the effects of outliers and maximize the safety margin for driving, the generated path is smooth and safe, while satisfying the constraint of vehicle kinematic.