Search Results

Lane keeping assist (LKA) is an autonomous driving technique that enables vehicles to travel along a desired line of lanes by adjusting the front steering angle. Reinforcement learning (RL) is one kind of machine learning. Agents or machines are not told how to act but instead learn from interaction with the environment. It also frees us from coding complex policies manually. But it has not yet been successfully applied to autonomous driving. Two control strategies using different deep reinforcement learning (DRL) algorithms have been proposed and used in the lane keeping assist scenario in this paper. Deep Q-network (DQN) algorithm with discrete action space and deep deterministic policy gradient (DDPG) algorithm with continuous action space have been implemented, respectively. Based on MATLAB/Simulink, deep neural networks representing the control policy are designed. The environment as well as the vehicle dynamics are also modelled in Simulink.

Heat treated cast aluminum components like engine blocks and cylinder heads can develop significant amount of residual stress and distortion particularly with water quench. To incorporate the influence of residual stress and distortion in cast aluminum product design, a rapid simulation approach has been developed based on artificial neural network and component geometry characteristics. Multilayer feed-forward artificial neural network (ANN) models were trained and verified using FEA residual stress and distortion predictions together with part geometry information such as curvature, maximum dihedral angle, topologic features including node's neighbors, as well as quench parameters like quench temperature and quench media.

Nowadays, the rapid growth of civil aviation transportation demand has led to more frequent flight delays. The major problem of flight delays is restricting the development of municipal airports. To further improve passenger satisfaction, and reduce economic losses caused by flight delays, environmental pollution and many other adverse consequences, three machine learning algorithms are constructed in current study: random forest (RF), gradient boosting decision tree (GBDT) and BP neural network (BPNN). The departure flight delay prediction model uses the actual data set of domestic flights in the United States to simulate and verify the performance and accuracy of the three models. This model combines the visual analysis system to show the density of departure flight delays between different airports. Firstly, the data set is reprocessed, and the main factors leading to flight delays are selected as sample attributes by principal component analysis.