Romanus: Robust Task Offloading in Modular Multi-Sensor Autonomous Driving Systems
This work addresses energy consumption and safety issues in autonomous driving systems, offering a domain-specific solution that is incremental by building on existing edge computing and offloading techniques.
The paper tackles the challenge of energy-efficient and robust task offloading in autonomous driving systems by proposing a method that uses deep reinforcement learning to adapt offloading based on scene complexity and network conditions, resulting in 14.99% higher energy efficiency and a 77.06% reduction in risky behavior compared to baselines.
Due to the high performance and safety requirements of self-driving applications, the complexity of modern autonomous driving systems (ADS) has been growing, instigating the need for more sophisticated hardware which could add to the energy footprint of the ADS platform. Addressing this, edge computing is poised to encompass self-driving applications, enabling the compute-intensive autonomy-related tasks to be offloaded for processing at compute-capable edge servers. Nonetheless, the intricate hardware architecture of ADS platforms, in addition to the stringent robustness demands, set forth complications for task offloading which are unique to autonomous driving. Hence, we present $ROMANUS$, a methodology for robust and efficient task offloading for modular ADS platforms with multi-sensor processing pipelines. Our methodology entails two phases: (i) the introduction of efficient offloading points along the execution path of the involved deep learning models, and (ii) the implementation of a runtime solution based on Deep Reinforcement Learning to adapt the operating mode according to variations in the perceived road scene complexity, network connectivity, and server load. Experiments on the object detection use case demonstrated that our approach is 14.99% more energy-efficient than pure local execution while achieving a 77.06% reduction in risky behavior from a robust-agnostic offloading baseline.