Comparison of Different Methods for Time Sequence Prediction in Autonomous Vehicles
This is an incremental study comparing existing methods for time sequence prediction in autonomous vehicles, which is important for improving safety and decision-making in self-driving systems.
The paper tackled the problem of forecasting time series for autonomous vehicles by comparing nearest neighborhood, fuzzy coding, and LSTM methods on a real-world vehicle velocity dataset, with results analyzed for performance, merits, and drawbacks.
As a combination of various kinds of technologies, autonomous vehicles could complete a series of driving tasks by itself, such as perception, decision-making, planning, and control. Since there is no human driver to handle the emergency situation, future transportation information is significant for automated vehicles. This paper proposes different methods to forecast the time series for autonomous vehicles, which are the nearest neighborhood (NN), fuzzy coding (FC), and long short term memory (LSTM). First, the formulation and operational process for these three approaches are introduced. Then, the vehicle velocity is regarded as a case study and the real-world dataset is utilized to predict future information via these techniques. Finally, the performance, merits, and drawbacks of the presented methods are analyzed and discussed.