The existing variants of the rapidly exploring random tree (RRT) cannot be effectively applied in local path planning of the autonomous vehicle and solve the coherence problem of paths between the front and back frames. Thus, an improved heuristic Bi-RRT algorithm is proposed, which is suitable for obstacle avoidance of the vehicle in an unknown dynamic environment. The vehicle constraint considering the driver’s driving habit and the obstacle-free direct connection mode of two random trees are introduced. Multi-sampling biased towards the target state reduces invalid searches, and parent node selection with the comprehensive measurement index accelerates the algorithm’s execution while making the initial path gentle. The adaptive greedy step size, introducing the target direction, expands the node more effectively. Moreover, path reorganization minimizes redundant path points and makes the path’s curvature continuous, and path coherence makes paths between the frames connect smoothly. Simulation analysis clarifies the efficient performance of the proposed algorithm, which can generate the smoothest path within the shortest time compared with the other four algorithms. Furthermore, the experiments on dynamic environments further show that the proposed algorithm can generate a differentiable coherence path, ensuring the ride comfort and stability of the vehicle.
Given that the rapidly exploring random tree algorithm (RRT) and its variants cannot efficiently solve problems of path planning of autonomous vehicles, this paper proposes a new, adaptive improved RRT algorithm. Firstly, an adaptive directional sampling strategy is introduced to avoid excessive search by reducing the randomness of sampling points. Secondly, a reasonable node selection strategy is used to improve the smoothness of the path by utilizing a comprehensive criterion that combines angle and distance. Thirdly, an adaptive node expansion strategy is utilized to avoid invalid expansion and make the generated path more reasonable. Finally, the expanded ellipse is used to realize vehicle obstacle avoidance in advance, and the post-processing strategy removes redundant line segments of the initial path to improve its quality. The simulation results show that the quality of the planned path is significantly improved. This path followed successfully has good trajectory stability, which shows the proposed algorithm’s effectiveness and practicability in autonomous vehicles’ local path planning.
To improve the comfort of information cognition and safety in expressway long-tunnel exit, and to study the variation of drivers' visual features in expressway long-tunnel exit, medium passenger vehicle was used to perform driving test in real tunnel environment. Parameters of visual features were recorded using eye tracking system when vehicles traversed the section from 200 meters inside the tunnel to another spot 200 meters outside the tunnel. Mathematic models of drivers' fixation duration, the number of fixations, and saccade amplitude in the tunnel exit were established based on BP Neural Network (Error Back Propagation Network) simulation. Results showed that as the vehicle moving closer to the tunnel exit, fixation duration and the number of fixations gradually decreased, while saccade amplitude increased. After drivers left the tunnel exit, fixation duration slightly decreased and the number of fixations increased, while saccade amplitude was slightly bigger than that inside the tunnel, only with litter amplitude variation.
Based on the theory of driving stress training and impetus customization, a driver stress training system was designed to reduce traffic accidents because of drivers' lack of stress response ability when driving on the rural road. According to the characters of traffic accidents on rural roads, stress scenes were developed. In the experiment, 30 subjects were selected to attend typical conditions for the virtual simulation rural road driving experiment on the system platform. Heart rate was detected by MP150 simultaneously to indicate any variation of stress response ability. Experimental data was analysed using logarithmic regression and relativity analysis. The model between the stress level of this stress system and the training times was established, and the matching training standard was put forward. The results showed that stress response ability was strengthened with the addition of training times. Trained on different stress driving scenes under urban road condition according to the established training standards, driver was relaxed and response ability was promoted. Demands of stress response were satisfied by the training system and standards established. Stress response ability of drivers can be promoted and these types of traffic accidents can be reduced efficiently.
The management of dangerous goods transportation is essential for reducing accidents and ensuring transportation safety. Few integration studies have specified management both in normal and emergent situations, therefore, an emergency management system for dangerous goods transportation was constructed based on ArcGIS. Visual Studio 2010 and SQL Server were adopted as the development platform and database, respectively. An information map of dangerous goods transportation enterprises was portrayed by ArcGIS. ArcGIS Engine combined with the C# language was utilized for secondary development and emergency management system resulting in both geographical coordinates and enterprise location. This system could present key information of enterprises from multiple perspectives. The shortest paths and best rescue strategies under emergency were further investigated via data mining. Finally, data of Guizhou province were applied. This research would directly manage dangerous goods transportation in an intuitive way, so as to provide decision making strategies for an enterprise manager.
Route optimization is one of most effective measures for reducing the hazardous materials transportation risk by road. This paper discusses the problem related to route optimization for hazardous materials transportation with multiple time-windows constraints and time-varying attributes and for a given OD pair. Based on establishing a mathematical model for the above-mentioned route optimization problem, the proposed mathematical model is equivalently transformed into a static multi-objective shortest route problem reconstructed by the space-time network techniques, and an efficient dynamic labeling algorithm which can identify the most satisfied route is then developed. Finally, an example is taken for analyzing the effectiveness and practicability of the above-proposed method and algorithm. The result shows that the established route optimization model and algorithm have better operability in solving such complexity problem, which can provide technical support to decision-making of the government authorities and the road hazmat transport enterprises.