$μ$Drive: User-Controlled Autonomous Driving
Kun Wang, Christopher M. Poskitt, Yang Sun, Jun Sun, Jingyi Wang, Peng Cheng, Jiming Chen
TL;DR
μDrive addresses the challenge of aligning autonomous vehicle planning with rider preferences by introducing an event-based DSL that intervenes in the planning module. It is implemented on top of Apollo and Apollo Studio, with a parser and interface that map rules to planning parameter changes and support online actions for real-time control. Evaluation against traffic-regulation benchmarks shows that μDrive interventions significantly improve compliance while maintaining millisecond-to-second level response times. This work provides a practical, platform-agnostic path toward personalized, user-centric AVs and suggests future integration with LLM-based automatic rule generation.
Abstract
Autonomous Vehicles (AVs) rely on sophisticated Autonomous Driving Systems (ADSs) to provide passengers a satisfying and safe journey. The individual preferences of riders plays a crucial role in shaping the perception of safety and comfort while they are in the car. Existing ADSs, however, lack mechanisms to systematically capture and integrate rider preferences into their planning modules. To bridge this gap, we propose $μ$Drive, an event-based Domain-Specific Language (DSL) designed for specifying autonomous vehicle behaviour. $μ$Drive enables users to express their preferences through rules triggered by contextual events, such as encountering obstacles or navigating complex traffic situations. These rules dynamically adjust the parameter settings of the ADS planning module, facilitating seamless integration of rider preferences into the driving plan. In our evaluation, we demonstrate the feasibility and efficacy of $μ$Drive by integrating it with the Apollo ADS framework. Our findings show that users can effectively influence Apollo's planning through $μ$Drive, assisting ADS in achieving improved compliance with traffic regulations. The response time for $μ$Drive commands remains consistently at the second or millisecond level. This suggests that $μ$Drive may help pave the way to more personalizsed and user-centric AV experiences.