No abstract

No abstract

In order to safely and comfortably navigate in the complex urban traffic, it is necessary to make multi-modal predictions of autonomous vehicles for the next trajectory of various traffic participants, with the continuous movement trend and inertia of the surrounding traffic agents taken into account. At present, most trajectory prediction methods focus on prediction on future behavior of traffic agents but with limited, consideration of the response of traffic agents to the future behavior of the ego-agent. Moreover, it can only predict the trajectory of single-type agents, which make it impossible to learn interaction in a complex environment between traffic agents. In this paper, we proposed a graph-based heterogeneous traffic agents trajectory prediction model LSTGHP, which consists of the following three parts: (1) layered spatio-temporal graph module; (2) ego-agent motion module; (3) trajectory prediction module, which can realize multi-modal prediction of future trajectories of traffic agents with different semantic categories in the scene. To evaluate its performance, we collected trajectory datasets of heterogeneous traffic agents in a time-varying, highly dynamic urban intersection environment, where vehicles, bicycles, and pedestrians interacted with each other in the scene. It can be drawn from experimental results that our model can improve its prediction accuracy while interacting at a close range. Compared with the previous prediction methods, the model has less prediction error in the trajectory prediction of heterogeneous traffic agents.

An efficient approach for lane marking detection and classification by the combination of convolution neural network and recurrent neural network is proposed in this paper. First, convolution neural network is trained for lane marking features extraction, and then these convolution neural network features of continuous frames are transferred to recurrent neural network model for lane boundary detection and classification in the time domain. At last, a lane boundary fitting method based on dynamic programming is proposed to improve the lane detection accuracy and robustness. The method presented generates satisfactory results of lane detection and type classification under various traffic conditions according to the experimental results, which show that the approach provided in this paper outperforms traditional methods and the total lane markings classification reached 95.21% accuracy.

Porous [d=per]materials arematerial is a new type of engineering material with both functional and structural properties. Compared with regular porous [d=per]structures and random porous structures, a gradientstructure and the random porous structure, gradient porous structure is a porous structure with a spatial variation mechanism, which can adjust the layout of the structure by changing its own load and boundary conditions according to different situations, thus obtaining better performance. In this paper, three spatial Voronoi structures with different spatial gradients are designed [d=per]using theby spatial Voronoi tessellation method. The differences in thermal protection [d=per]performancesperformance between the Voronoi spatial gradient structure and the regular structure and the effects of porosity, gradient direction and heat flow density on the three-dimensional Voronoi stochastic gradient structure were investigated [d=per]viaby data simulation. The results show that the effective thermal conductivity of the Voronoi spatial gradient structure is lower than that of the regular structure. The effective thermal conductivity of the structure gradually decreases with increasing porosity. Taking the gradient Voronoi structure consisting of 3×3×3 units as an example, when the porosity increases from 83% to 94.98%, its effective thermal conductivity decreases from 0.586 to 0.149 Wm−1K−1. The anisotropy of the random structure leads to effective thermal conductivity errors of more than 5% in all three gradient directions. In addition, according to the principle of thermal resistance superposition, we designed a battery pack set for calculating the effective thermal [d=per]conductivitiesconductivity of pillar-based porous materials, including three-dimensional Voronoi gradient random porous materials on the Grasshopper platform. In this way, the effective thermal conductivity of a pillar-based porous material can be predicted more accurately. The predicted calculation results and the simulation results basically agree with each other, and the relative errors of both are within 10%.