Comparison of Different Methods for Time Sequence Prediction in Autonomous Vehicles

TL;DR

This paper compares three different methods—nearest neighborhood, fuzzy coding, and LSTM—for predicting future vehicle velocity in autonomous vehicles, analyzing their effectiveness and limitations using real-world data.

Contribution

It introduces and evaluates three distinct time series prediction methods specifically applied to autonomous vehicle velocity forecasting.

Findings

LSTM outperforms other methods in prediction accuracy.

Fuzzy coding offers robustness in noisy data scenarios.

Nearest neighborhood is computationally efficient but less accurate.

Abstract

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.