Aurora framework makes air ground co simulation more reliable and verifiable
AURORA: A Natural Language-Driven Agentic Framework for Understanding, Reasoning, and Orchestrating Reliable Air-Ground Co-Simulation
RoboticsArtificial Intelligence
Summary
Simulating coordinated air and ground transportation can be really hard and time-consuming, especially when making sure the scenarios follow all the rules and interactions intended. The authors introduce AURORA, a system that turns natural language instructions into detailed simulation plans while checking step-by-step that all conditions are met. This method helps catch hidden errors that might not stop a scenario from running but would break its intended logic. They also created a benchmark to test if simulations truly behave as requested, improving trust and fixing problems without starting over.
What this means in practice
- •For transportation simulation developers: Create verified air-ground transportation scenarios from natural language to reduce manual work and improve scenario reliability.
- •For urban planning teams: Use reliable simulation scenarios to test and verify urban airspace and traffic interactions before real-world deployment.
Authors
Keshu Wu, Hao Zhang, Rui Gan, Xiangbo Gao, Xiaopeng Li, Zhengzhong Tu, Yang Zhou
Abstract
Air-ground transportation research increasingly relies on co-simulation, yet constructing scenarios remains labor-intensive and difficult to validate. More importantly, a generated scenario may execute successfully while failing to realize the spatial, temporal, communication, or behavioral relationships requested by the user. This paper presents AURORA, a natural-language-driven agentic framework that treats air-ground scenario generation as a process of compilation with verification. Central to AURORA is the Air-Ground Scenario Graph (AGSG), a typed intermediate representation that explicitly connects agents, aerial missions, events, communication links, success conditions, and their cross-domain dependencies. This shared representation enables simulator-grounded parsing, joint road-airspace grounding, temporal planning, pre-execution feasibility checking, trace-based runtime verification, failure localization, and bounded repair within a unified workflow. We further introduce AURORA-Bench to evaluate not only whether generated scenarios execute, but whether they faithfully realize the requested interactions. Experiments across multiple language models show that structured execution substantially improves reliability, while runtime verification exposes silent failures that completion-based evaluation overlooks. Localized repair further resolves many violations without regenerating the entire scenario. The results show that reliable scenario generation requires verifying realized behavior, not merely executable code, and demonstrate the value of explicit intermediate representations for verifiable and repairable language-driven co-simulation.