Driver Action Prediction Using Deep (Bidirectional) Recurrent Neural Network

TL;DR

This paper presents a real-time driver action prediction system using a deep bidirectional recurrent neural network that effectively combines multi-modal sensory data to forecast key driver behaviors up to 5 seconds in advance.

Contribution

It introduces a novel real-time framework integrating camera and vehicle data with a deep bidirectional RNN for early driver action prediction.

Findings

Outperforms existing systems in driver action prediction accuracy.

Successfully predicts acceleration, braking, lane change, and turning actions.

Achieves 5-second prediction horizon with high reliability.

Abstract

Advanced driver assistance systems (ADAS) can be significantly improved with effective driver action prediction (DAP). Predicting driver actions early and accurately can help mitigate the effects of potentially unsafe driving behaviors and avoid possible accidents. In this paper, we formulate driver action prediction as a timeseries anomaly prediction problem. While the anomaly (driver actions of interest) detection might be trivial in this context, finding patterns that consistently precede an anomaly requires searching for or extracting features across multi-modal sensory inputs. We present such a driver action prediction system, including a real-time data acquisition, processing and learning framework for predicting future or impending driver action. The proposed system incorporates camera-based knowledge of the driving environment and the driver themselves, in addition to traditional vehicle dynamics. It then uses a deep bidirectional recurrent neural network (DBRNN) to learn the correlation between sensory inputs and impending driver behavior achieving accurate and high horizon action prediction. The proposed system performs better than other existing systems on driver action prediction tasks and can accurately predict key driver actions including acceleration, braking, lane change and turning at durations of 5sec before the action is executed by the driver.