Car-following is an essential trajectory control strategy for the autonomous vehicle, which not only improves traffic efficiency, but also reduces fuel consumption and emissions. However, the prediction of lane change intentions in adjacent lanes is problematic, and will significantly affect the car-following control of the autonomous vehicle, especially when the vehicle changing lanes is only a connected unintelligent vehicle without expensive and accurate sensors. Autonomous vehicles suffer from adjacent vehicles’ abrupt lane changes, which may reduce ride comfort and increase energy consumption, and even lead to a collision. A machine learning-based lane change intention prediction and real time autonomous vehicle controller is proposed to respond to this problem. First, an interval-based support vector machine is designed to predict the vehicles’ lane change intention utilizing limited low-level vehicle status through vehicle-to-vehicle communication. Then, a conditional artificial potential field method is used to design the car-following controller by incorporating the lane-change intentions of the vehicle. Experimental results reveal that the proposed method can estimate a vehicle’s lane change intention more accurately. The autonomous vehicle avoids collisions with a lane-changing connected unintelligent vehicle with reliable safety and favorable dynamic performance.

The interaction and sharing of data based on network users make network information overexpanded, and “information overload” has become a difficult problem for everyone. The information filtering technology based on recommendation could dig out the needs and hobbies of users from the historical behavior, historical data, and social network and filter out useful resource for users in accordance with the needs and hobbies from the accumulation of information resource. Collaborative filtering is one of the core technologies in the recommendation system and is also the most widely used and most effective recommendation algorithm. In this paper, we study the accuracy and the data sparsity problems of recommendation algorithm. On the basis of the conventional algorithm, we combine the user score probability and take the commodity type into consideration when calculating similarity. The algorithm based on user score probability and project type (UPCF) is proposed, and the experimental data set from the recommendation system is used to validate and analyze data. The experimental results show that the UPCF algorithm alleviates the sparsity of data to a certain extent and has better performance than the conventional algorithms.