# Robust and Subject-Independent Driving Manoeuvre Anticipation through Domain-Adversarial Recurrent Neural Networks

## TL;DR

This paper introduces a domain-adversarial RNN approach for robust driving maneuver prediction that adapts to new drivers and vehicles, significantly improving performance in diverse scenarios.

## Contribution

It presents a novel application of domain-adversarial training to driving data, enabling domain-invariant feature learning for better maneuver anticipation across different drivers and vehicles.

## Key findings

- 30% performance increase on Brain4Cars dataset
- 114% performance increase on simulated data
- Effective fine-tuning enhances domain invariance

## Abstract

Through deep learning and computer vision techniques, driving manoeuvres can be predicted accurately a few seconds in advance. Even though adapting a learned model to new drivers and different vehicles is key for robust driver-assistance systems, this problem has received little attention so far. This work proposes to tackle this challenge through domain adaptation, a technique closely related to transfer learning. A proof of concept for the application of a Domain-Adversarial Recurrent Neural Network (DA-RNN) to multi-modal time series driving data is presented, in which domain-invariant features are learned by maximizing the loss of an auxiliary domain classifier. Our implementation is evaluated using a leave-one-driver-out approach on individual drivers from the Brain4Cars dataset, as well as using a new dataset acquired through driving simulations, yielding an average increase in performance of 30% and 114% respectively compared to no adaptation. We also show the importance of fine-tuning sections of the network to optimise the extraction of domain-independent features. The results demonstrate the applicability of the approach to driver-assistance systems as well as training and simulation environments.