# Attention-based Lane Change Prediction

## TL;DR

This paper introduces an attention-based recurrent model for lane change prediction that emphasizes both accuracy and interpretability, incorporating new metrics to assess driver discomfort, with promising results on multiple datasets.

## Contribution

The paper presents a novel attention-based recurrent model that improves interpretability and prediction accuracy for lane change prediction tasks.

## Key findings

- Encouraging results on publicly available dataset
- Effective modeling of corner and failure cases
- Introduction of metrics reflecting driver discomfort

## Abstract

Lane change prediction of surrounding vehicles is a key building block of path planning. The focus has been on increasing the accuracy of prediction by posing it purely as a function estimation problem at the cost of model understandability. However, the efficacy of any lane change prediction model can be improved when both corner and failure cases are humanly understandable. We propose an attention-based recurrent model to tackle both understandability and prediction quality. We also propose metrics which reflect the discomfort felt by the driver. We show encouraging results on a publicly available dataset and proprietary fleet data.