Development and testing of an image transformer for explainable autonomous driving systems

by   Jiqian Dong, et al.

In the last decade, deep learning (DL) approaches have been used successfully in computer vision (CV) applications. However, DL-based CV models are generally considered to be black boxes due to their lack of interpretability. This black box behavior has exacerbated user distrust and therefore has prevented widespread deployment DLCV models in autonomous driving tasks even though some of these models exhibit superiority over human performance. For this reason, it is essential to develop explainable DL models for autonomous driving task. Explainable DL models can not only boost user trust in autonomy but also serve as a diagnostic approach to identify anydefects and weaknesses of the model during the system development phase. In this paper, we propose an explainable end-to-end autonomous driving system based on "Transformer", a state-of-the-art (SOTA) self-attention based model, to map visual features from images collected by onboard cameras to guide potential driving actions with corresponding explanations. The model achieves a soft attention over the global features of the image. The results demonstrate the efficacy of our proposed model as it exhibits superior performance (in terms of correct prediction of actions and explanations) compared to the benchmark model by a significant margin with lower computational cost.


page 8

page 11


Reason induced visual attention for explainable autonomous driving

Deep learning (DL) based computer vision (CV) models are generally consi...

Explaining Autonomous Driving by Learning End-to-End Visual Attention

Current deep learning based autonomous driving approaches yield impressi...

Explainability of vision-based autonomous driving systems: Review and challenges

This survey reviews explainability methods for vision-based self-driving...

Attribution-based XAI Methods in Computer Vision: A Review

The advancements in deep learning-based methods for visual perception ta...

Explainable Object-induced Action Decision for Autonomous Vehicles

A new paradigm is proposed for autonomous driving. The new paradigm lies...

A new interpretable unsupervised anomaly detection method based on residual explanation

Despite the superior performance in modeling complex patterns to address...

Explainable Deep Learning to Profile Mitochondrial Disease Using High Dimensional Protein Expression Data

Mitochondrial diseases are currently untreatable due to our limited unde...

Please sign up or login with your details

Forgot password? Click here to reset