A Generalized Control Revision Method for Autonomous Driving Safety

TL;DR

This paper introduces a generalized control revision method for autonomous driving that integrates perception data and traffic scene constraints to enhance safety in complex environments, demonstrating effectiveness in simulation and real-world tests.

Contribution

It proposes a unified control revision framework using a new barrier function that handles heterogeneous perception data and diverse traffic scenarios.

Findings

Effective safety control revision in complex scenes

Compatibility with various planning backbones and road types

Validated on both simulators and real-world platform

Abstract

Safety is one of the most crucial challenges of autonomous driving vehicles, and one solution to guarantee safety is to employ an additional control revision module after the planning backbone. Control Barrier Function (CBF) has been widely used because of its strong mathematical foundation on safety. However, the incompatibility with heterogeneous perception data and incomplete consideration of traffic scene elements make existing systems hard to be applied in dynamic and complex real-world scenarios. In this study, we introduce a generalized control revision method for autonomous driving safety, which adopts both vectorized perception and occupancy grid map as inputs and comprehensively models multiple types of traffic scene constraints based on a new proposed barrier function. Traffic elements are integrated into one unified framework, decoupled from specific scenario settings or rules. Experiments on CARLA, SUMO, and OnSite simulator prove that the proposed algorithm could realize safe control revision under complicated scenes, adapting to various planning backbones, road topologies, and risk types. Physical platform validation also verifies the real-world application feasibility.