Action-Based Representation Learning for Autonomous Driving

08/21/2020
by   Yi Xiao, et al.
9

Human drivers produce a vast amount of data which could, in principle, be used to improve autonomous driving systems. Unfortunately, seemingly straightforward approaches for creating end-to-end driving models that map sensor data directly into driving actions are problematic in terms of interpretability, and typically have significant difficulty dealing with spurious correlations. Alternatively, we propose to use this kind of action-based driving data for learning representations. Our experiments show that an affordance-based driving model pre-trained with this approach can leverage a relatively small amount of weakly annotated imagery and outperform pure end-to-end driving models, while being more interpretable. Further, we demonstrate how this strategy outperforms previous methods based on learning inverse dynamics models as well as other methods based on heavy human supervision (ImageNet).

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 3

page 6

page 13

03/13/2020

A Survey of End-to-End Driving: Architectures and Training Methods

Autonomous driving is of great interest to industry and academia alike. ...
10/22/2021

ModEL: A Modularized End-to-end Reinforcement Learning Framework for Autonomous Driving

Heated debates continue over the best autonomous driving framework. The ...
03/21/2020

End-to-end Autonomous Driving Perception with Sequential Latent Representation Learning

Current autonomous driving systems are composed of a perception system a...
09/11/2019

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

Autonomous driving is a multi-task problem requiring a deep understandin...
04/02/2021

Autonomous Driving Data Chain Interfaces

Recent developments in autonomous driving technology have proven that ma...
07/10/2020

Learning Accurate and Human-Like Driving using Semantic Maps and Attention

This paper investigates how end-to-end driving models can be improved to...
06/07/2019

Multimodal End-to-End Autonomous Driving

Autonomous vehicles (AVs) are key for the intelligent mobility of the fu...

Code Repositories

Action-Based-Representation-Learning

None


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.