RETHINKING SELF-DRIVING : MULTI -TASK KNOWLEDGE FOR BETTER GENERALIZATION AND ACCIDENT EXPLANATION ABILITY

Zhihao LI, Toshiyuki MOTOYOSHI, Kazuma SASAKI, Tetsuya OGATA, Shigeki SUGANO

Abstract:

Current end-to-end deep learning driving models have two problems: (1) Poor
generalization ability of unobserved driving environment when diversity of train-
ing driving dataset is limited (2) Lack of accident explanation ability when driving
models don’t work as expected. To tackle these two problems, rooted on the be-
lieve that knowledge of associated easy task is benificial for addressing difficult
task, we proposed a new driving model which is composed of perception module
for see and think and driving module for behave, and trained it with multi-task
perception-related basic knowledge and driving knowledge stepwisely. Specifi-
cally segmentation map and depth map (pixel level understanding of images) were
considered as what & where and how far knowledge for tackling easier driving-
related perception problems before generating final control commands for difficult
driving task. The results of experiments demonstrated the effectiveness of multi-
task perception knowledge for better generalization and accident explanation abil-
ity. With our method the average sucess rate of finishing most difficult navigation
tasks in untrained city of CoRL test surpassed current benchmark method for 15
percent in trained weather and 20 percent in untrained weathers.

Keywords: Autonomous car, convolution network, image segmentation, depth estimation, generalization ability, explanation ability, multi-task learning

TL;DR: we proposed a new self-driving model which is composed of perception module for see and think and driving module for behave to acquire better generalization and accident explanation ability.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/rethinking-self-driving-multi-task-knowledge/code)