GoonDAE: Denoising-Based Driver Assistance for Off-Road Teleoperation

TL;DR

GoonDAE is a real-time denoising autoencoder system that improves off-road teleoperation by assisting unskilled drivers, reducing training time and enhancing driving stability in dangerous environments.

Contribution

This paper introduces GoonDAE, a novel skip-connected LSTM-based denoising autoencoder for real-time driver assistance in off-road teleoperation, addressing skill gap issues.

Findings

Significantly improved driving stability with GoonDAE.

Effective denoising of unskilled driver inputs in simulation.

Reduced training time for unskilled drivers.

Abstract

Because of the limitations of autonomous driving technologies, teleoperation is widely used in dangerous environments such as military operations. However, the teleoperated driving performance depends considerably on the driver's skill level. Moreover, unskilled drivers need extensive training time for teleoperations in unusual and harsh environments. To address this problem, we propose a novel denoising-based driver assistance method, namely GoonDAE, for real-time teleoperated off-road driving. The unskilled driver control input is assumed to be the same as the skilled driver control input but with noise. We designed a skip-connected long short-term memory (LSTM)-based denoising autoencoder (DAE) model to assist the unskilled driver control input by denoising. The proposed GoonDAE was trained with skilled driver control input and sensor data collected from our simulated off-road driving environment. To evaluate GoonDAE, we conducted an experiment with unskilled drivers in the simulated environment. The results revealed that the proposed system considerably enhanced driving performance in terms of driving stability.