Perspectives on the System-level Design of a Safe Autonomous Driving Stack

TL;DR

This paper discusses a system-level approach to designing safe autonomous driving stacks, emphasizing safety by design, interpretable prediction, and effective transfer between simulation and real-world testing.

Contribution

It introduces novel methods for safe planning, verifiable prediction, and perception error modeling within an autonomous vehicle system.

Findings

Safe-by-design planning enhances safety robustness.

Verifiable prediction improves system interpretability.

Perception error modeling facilitates effective simulation-to-real transfer.

Abstract

Achieving safe and robust autonomy is the key bottleneck on the path towards broader adoption of autonomous vehicles technology. This motivates going beyond extrinsic metrics such as miles between disengagement, and calls for approaches that embody safety by design. In this paper, we address some aspects of this challenge, with emphasis on issues of motion planning and prediction. We do this through description of novel approaches taken to solving selected sub-problems within an autonomous driving stack, in the process introducing the design philosophy being adopted within Five. This includes safe-by-design planning, interpretable as well as verifiable prediction, and modelling of perception errors to enable effective sim-to-real and real-to-sim transfer within the testing pipeline of a realistic autonomous system.