vEDGAR - Can CARLA Do HiL?

2025-12-09

AI Summary

CARLA lacks real-time Hardware-in-the-Loop (HiL) simulation capabilities spanning the full sensor-actuator stack, hindering closed-loop validation of autonomous driving functions. To address this, we propose the first CARLA extension framework explicitly designed for HiL testing, integrating an enhanced CARLA simulator with the vEDGAR real-time simulation platform. Our framework enables high-fidelity sensor modeling, deterministic communication synchronization, hardware interface integration, and end-to-end closed-loop control execution. It supports low-latency, high-fidelity end-to-end testing on actual embedded computing hardware—marking the first time open-source CARLA achieves HiL-grade co-simulation and hardware-software performance evaluation. We publicly release a customized CARLA fork alongside the vEDGAR toolchain, significantly advancing automation, reproducibility, and consistency in autonomous driving verification workflows.

Technology Category

• Machine Learning: Hardware-aware ML
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Simulation offers advantages throughout the development process of automated driving functions, both in research and product development. Common open-source simulators like CARLA are extensively used in training, evaluation, and software-in-the-loop testing of new automated driving algorithms. However, the CARLA simulator lacks an evaluation where research and automated driving vehicles are simulated with their entire sensor and actuation stack in real time. The goal of this work is therefore to create a simulation framework for testing the automation software on its dedicated hardware and identifying its limits. Achieving this goal would greatly benefit the open-source development workflow of automated driving functions, designating CARLA as a consistent evaluation tool along the entire development process. To achieve this goal, in a first step, requirements are derived, and a simulation architecture is specified and implemented. Based on the formulated requirements, the proposed vEDGAR software is evaluated, resulting in a final conclusion on the applicability of CARLA for HiL testing of automated vehicles. The tool is available open source: Modified CARLA fork: https://github.com/TUMFTM/carla, vEDGAR Framework: https://github.com/TUMFTM/vEDGAR

Problem

• Develops a simulation framework for hardware-in-the-loop testing of automated driving software
• Enables real-time simulation of full sensor and actuation stacks in CARLA
• Evaluates CARLA's applicability as a consistent tool throughout development workflow

Innovation

• Extended CARLA for real-time sensor simulation
• Created vEDGAR framework for hardware-in-the-loop testing
• Open-source tools for full-stack automated vehicle evaluation