Reimagining an autonomous vehicle

TL;DR

This paper advocates for a fundamental rethinking of autonomous vehicle technology, proposing a new vision called AV2.0 that leverages recent knowledge and machine learning to address current limitations and guide future research.

Contribution

It introduces the concept of AV2.0, a reimagined autonomous vehicle paradigm based on recent advancements and machine learning, challenging traditional approaches.

Findings

Current AV tech is based on outdated decisions from a decade ago.

A new vision, AV2.0, is proposed to guide future research.

Identifies grand challenges for machine learning in autonomous driving.

Abstract

The self driving challenge in 2021 is this century's technological equivalent of the space race, and is now entering the second major decade of development. Solving the technology will create social change which parallels the invention of the automobile itself. Today's autonomous driving technology is laudable, though rooted in decisions made a decade ago. We argue that a rethink is required, reconsidering the autonomous vehicle (AV) problem in the light of the body of knowledge that has been gained since the DARPA challenges which seeded the industry. What does AV2.0 look like? We present an alternative vision: a recipe for driving with machine learning, and grand challenges for research in driving.