To address the problem of model error and tracking dependence in the process of intelligent vehicle motion planning, an intelligent vehicle model transfer trajectory planning method based on deep reinforcement learning is proposed, which is able to obtain an effective control action sequence directly. Firstly, an abstract model of the real environment is extracted. On this basis, a deep deterministic policy gradient (DDPG) and a vehicle dynamic model are adopted to jointly train a reinforcement learning model, and to decide the optimal intelligent driving maneuver. Secondly, the actual scene is transferred to an equivalent virtual abstract scene using a transfer model. Furthermore, the control action and trajectory sequences are calculated according to the trained deep reinforcement learning model. Thirdly, the optimal trajectory sequence is selected according to an evaluation function in the real environment. Finally, the results demonstrate that the proposed method can deal with the problem of intelligent vehicle trajectory planning for continuous input and continuous output. The model transfer method improves the model’s generalization performance. Compared with traditional trajectory planning, the proposed method outputs continuous rotation-angle control sequences. Moreover, the lateral control errors are also reduced.

The Jump Point Search (JPS) algorithm is adopted for local path planning of the driverless car under urban environment, and it is a fast search method applied in path planning. Firstly, a vector Geographic Information System (GIS) map, including Global Positioning System (GPS) position, direction, and lane information, is built for global path planning. Secondly, the GIS map database is utilized in global path planning for the driverless car. Then, the JPS algorithm is adopted to avoid the front obstacle, and to find an optimal local path for the driverless car in the urban environment. Finally, 125 different simulation experiments in the urban environment demonstrate that JPS can search out the optimal and safety path successfully, and meanwhile, it has a lower time complexity compared with the Vector Field Histogram (VFH), the Rapidly Exploring Random Tree (RRT), A*, and the Probabilistic Roadmaps (PRM) algorithms. Furthermore, JPS is validated usefully in the structured urban environment.

RGBT tracking is rapidly developing due to its complementary advantages of RGB and thermal frames. Existing methods with high accuracy track at a lower speed, and do not make full use of the hierarchical information in the feature extraction and the historical information of the sequences. To address these issues, a novel dual-modality space-time memory (DMSTM) network is proposed for robust RGBT tracking. Specifically, DMSTM is divided into three modules. The first module is the dual-modality backbone that utilizes both shallow and deep information by aggregating feature maps of dimensional changes during downsampling. Another module is the space-time memory reader with bimodal fusion. It aggregates features of historical and current frames to share information in the time domain. The last module is the siamese head network, which computes the predicted loss sum of the two modalities and back-propagates it. This avoids degrading the tracking performance due to sequence frame pairs where the training targets are not perfectly aligned. Extensive experiments on three RGBT benchmark datasets show that the performance and efficiency of the proposed DMSTM exceed that of state-of-the-art methods while running at 27.6 FPS.

Currently, since the model of a driverless bus is not clear, it is difficult for most traditional path tracking methods to achieve a trade-off between accuracy and stability, especially in the case of driverless buses. In terms of solving this problem, a path-tracking controller based on a Fuzzy Pure Pursuit Control with a Front Axle Reference (FPPC-FAR) is proposed in this paper. Firstly, the reference point of Pure Pursuit is moved from the rear axle to the front axle. It relieves the influence caused by the ignorance of the bus’s lateral dynamic characteristics and improves the stability of Pure Pursuit. Secondly, a fuzzy parameter self-tuning method is applied to improve the accuracy and robustness of the path-tracking controller. Thirdly, a feedback-feedforward control algorithm is devised for velocity control, which enhances the velocity tracking efficiency. The proportional-integral (PI) controller is indicated for feedback control, and the gravity acceleration component in the car’s forward direction is used in feedforward control. Finally, a series of experiments is conducted to illustrate the excellent performances of proposed methods.

Path planning for mobile robots in complex circumstances is still a challenging issue. This work introduces an improved deep reinforcement learning strategy for robot navigation that combines dueling architecture, Prioritized Experience Replay, and shaped Rewards. In a grid world and two Gazebo simulation environments with static and dynamic obstacles, the Dueling Deep Q-Network with Modified Rewards and Prioritized Experience Replay (PMR-Dueling DQN) algorithm is compared against Q-learning, DQN, and DDQN in terms of path optimality, collision avoidance, and learning speed. To encourage the best routes, the shaped Reward function takes into account target direction, obstacle avoidance, and distance. Prioritized replay concentrates training on important events while a dueling architecture separates value and advantage learning. The results show that the PMR-Dueling DQN has greatly increased convergence speed, stability, and overall performance across conditions. In both grid world and Gazebo environments the PMR-Dueling DQN achieved higher cumulative rewards. The combination of deep reinforcement learning with reward design, network architecture, and experience replay enables the PMR-Dueling DQN to surpass traditional approaches for robot path planning in complex environments.