Experimental Assessment of a Forward-Collision Warning System Fusing Deep Learning and Decentralized Radio Sensing

TL;DR

This paper proposes and experimentally evaluates a forward-collision warning system that combines deep learning with decentralized radio sensing, using vehicle-to-vehicle signals to detect oncoming vehicles on highways.

Contribution

It introduces a novel decentralized radio sensing approach integrated with deep learning for vehicle collision warning, validated through real-world highway field trials.

Findings

High detection accuracy achieved with both LSTM and CNN models.

Feasibility demonstrated for real-time collision warning using existing vehicular communication signals.

System effective in high-speed highway scenarios.

Abstract

This paper presents the idea of an automatic forward-collision warning system based on a decentralized radio sensing (RS) approach. In this framework, a vehicle in receiving mode employs a continuous waveform (CW) transmitted by a second vehicle as a probe signal to detect oncoming vehicles and warn the driver of a potential forward collision. Such a CW can easily be incorporated as a pilot signal within the data frame of current multicarrier vehicular communication systems. Detection of oncoming vehicles is performed by a deep learning (DL) module that analyzes the features of the Doppler signature imprinted on the CW probe signal by a rapidly approaching vehicle. This decentralized CW RS approach was assessed experimentally using data collected by a series of field trials conducted in a two-lanes high-speed highway. Detection performance was evaluated for two different DL models: a long short-term memory network and a convolutional neural network. The obtained results demonstrate the feasibility of the envisioned forward-collision warning system based on the fusion of DL and decentralized CW RS.