Bridging Simulation and Usability: A User-Friendly Framework for Scenario Generation in CARLA

TL;DR

This framework features a graphical interface that enables users to create, modify, save, load, and execute scenarios without needing coding expertise or detailed simulation knowledge, and increases the accessibility of simulation-based validation for researchers, engineers, and policymakers.

Abstract

Autonomous driving promises safer roads, reduced congestion, and improved mobility, yet validating these systems across diverse conditions remains a major challenge. Real-world testing is expensive, time-consuming, and sometimes unsafe, making large-scale validation impractical. In contrast, simulation environments offer a scalable and cost-effective alternative for rigorous verification and validation. A critical component of the validation process is scenario generation, which involves designing and configuring traffic scenarios to evaluate autonomous systems' responses to various events and uncertainties. However, existing scenario generation tools often require programming knowledge, limiting accessibility for non-technical users. To address this limitation, we present an interactive, no-code framework for scenario generation. Our framework features a graphical interface that enables users to create, modify, save, load, and execute scenarios without needing coding expertise or detailed simulation knowledge. Unlike script-based tools such as Scenic or ScenarioRunner, our approach lowers the barrier to entry and supports a broader user base. Central to our framework is a graph-based scenario representation that facilitates structured management, supports both manual and automated generation, and enables integration with deep learning-based scenario and behavior generation methods. In automated mode, the framework can randomly sample parameters such as actor types, behaviors, and environmental conditions, allowing the generation of diverse and realistic test datasets. By simplifying the scenario generation process, this framework supports more efficient testing workflows and increases the accessibility of simulation-based validation for researchers, engineers, and policymakers.

Figures (6)

• Figure 1: Overview of the proposed scenario generation workflow. The process begins with a one-time data management step, where the framework integrates a catalog of available OpenDRIVE maps and metadata, such as actor blueprints and environmental presets. Scenario creation then follows an intuitive flow: users select a map, define a region of interest (ROI), configure scenario parameters, and execute the scenario within the CARLA simulator.
• Figure 2: A catalog of OpenDrive maps extracted from CARLA, each annotated with statistical metadata, such as the number of junctions, crosswalks, and traffic lights, to help users identify a suitable map for scenario generation.
• Figure 3: Visualization of the graph-based representation for a simplified map segment. Blue nodes indicate potential spawn locations for road-bound actors, while yellow nodes represent possible pedestrian spawn points. Directed edges—black for successor connections, green for right, and red for left—define the spatial relations between road-bound actor nodes. In contrast, undirected edges are used for pedestrians to capture their flexible movement.
• Figure 4: Interactive process for defining the ROI used in scenario generation. The interface guides users in selecting an initial ROI and expanding it through adjacent, connected regions, ensuring spatial continuity in the overall scenario ROI.
• Figure 5: User-guided configuration workflow for scenario generation. The interface supports sequential selection of environmental conditions, NPC placement, goal assignment, and behavioral parameter configuration.