Human Visual Attention Prediction Boosts Learning & Performance of Autonomous Driving Agents

09/11/2019
by   Alexander Makrigiorgos, et al.
0

Autonomous driving is a multi-task problem requiring a deep understanding of the visual environment. End-to-end autonomous systems have attracted increasing interest as a method of learning to drive without exhaustively programming behaviours for different driving scenarios. When humans drive, they rely on a finely tuned sensory system which enables them to quickly acquire the information they need while filtering unnecessary details. This ability to identify task-specific high-interest regions within an image could be beneficial to autonomous driving agents and machine learning systems in general. To create a system capable of imitating human gaze patterns and visual attention, we collect eye movement data from human drivers in a virtual reality environment. We use this data to train deep neural networks predicting where humans are most likely to look when driving. We then use the outputs of this trained network to selectively mask driving images using a variety of masking techniques. Finally, autonomous driving agents are trained using these masked images as input. Upon comparison, we found that a dual-branch architecture which processes both raw and attention-masked images substantially outperforms all other models, reducing error in control signal predictions by 25.5% compared to a standard end-to-end model trained only on raw images.

READ FULL TEXT

page 1

page 2

page 4

page 5

research
12/05/2018

Visual Attention for Behavioral Cloning in Autonomous Driving

The goal of our work is to use visual attention to enhance autonomous dr...
research
10/13/2022

Learning Driving Policies for End-to-End Autonomous Driving

Humans tend to drive vehicles efficiently by relying on contextual and s...
research
07/30/2021

Brain-Inspired Deep Imitation Learning for Autonomous Driving Systems

Autonomous driving has attracted great attention from both academics and...
research
01/10/2018

Unsupervised Real-to-Virtual Domain Unification for End-to-End Highway Driving

In the spectrum of vision-based autonomous driving, vanilla end-to-end m...
research
06/26/2016

Fast Incremental Learning for Off-Road Robot Navigation

A promising approach to autonomous driving is machine learning. In such ...
research
05/02/2021

A LiDAR Assisted Control Module with High Precision in Parking Scenarios for Autonomous Driving Vehicle

Autonomous driving has been quite promising in recent years. The public ...
research
03/30/2017

Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention

Deep neural perception and control networks are likely to be a key compo...

Please sign up or login with your details

Forgot password? Click here to reset