Reimagining an autonomous vehicle

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.

arXiv commentUnder review

References in corpus (14)

• Towards A Rigorous Science of Interpretable Machine Learning
• A Survey of Autonomous Driving: Common Practices and Emerging Technologies
• Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
• Towards a Definition of Disentangled Representations
• TNT: Target-driveN Trajectory Prediction
• One Thousand and One Hours: Self-driving Motion Prediction Dataset
• Argoverse: 3D Tracking and Forecasting with Rich Maps
• FISHING Net: Future Inference of Semantic Heatmaps In Grids
• Invariant Causal Prediction for Block MDPs
• Safe Option-Critic: Learning Safety in the Option-Critic Architecture
• RMA: Rapid Motor Adaptation for Legged Robots
• FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras
• CARLA Real Traffic Scenarios -- novel training ground and benchmark for autonomous driving
• Universal Off-Policy Evaluation