A Serverless Edge-Native Data Processing Architecture for Autonomous Driving Training

TL;DR

This paper presents Lambda, a serverless edge-native platform for efficient, real-time data filtering and processing in autonomous driving systems, enabling better training data collection with reduced latency.

Contribution

It introduces Lambda, an edge-native, serverless-inspired framework that simplifies on-vehicle data filtering and processing using FaaS principles compatible with ROS 2.

Findings

Competitive performance on NVIDIA Jetson Orin Nano

Reduced latency and jitter compared to native ROS 2

Supports real-time data processing in embedded systems

Abstract

Data is both the key enabler and a major bottleneck for machine learning in autonomous driving. Effective model training requires not only large quantities of sensor data but also balanced coverage that includes rare yet safety-critical scenarios. Capturing such events demands extensive driving time and efficient selection. This paper introduces the Lambda framework, an edge-native platform that enables on-vehicle data filtering and processing through user-defined functions. The framework provides a serverless-inspired abstraction layer that separates application logic from low-level execution concerns such as scheduling, deployment, and isolation. By adapting Function-as-a-Service (FaaS) principles to resource-constrained automotive environments, it allows developers to implement modular, event-driven filtering algorithms while maintaining compatibility with ROS 2 and existing data recording pipelines. We evaluate the framework on an NVIDIA Jetson Orin Nano and compare it against native ROS 2 deployments. Results show competitive performance, reduced latency and jitter, and confirm that lambda-based abstractions can support real-time data processing in embedded autonomous driving systems. The source code is available at https://github.com/LASFAS/jblambda.