Scenario Orchestration for Closed-loop Policy Evaluation of Autonomous Driving
cs.RO
Submitted: 2026-11-06
Updated: 2026-11-06
Comments: 8 pages, 5 figures
License: http://creativecommons.org/licenses/by/4.0/
The gist: Scenario-based simulation is central to evaluating autonomous-driving policies, but a scenario scripted before execution (i.e., with predetermined…
Terminology
Abstract
Scenario-based simulation is central to evaluating autonomous-driving policies, but a scenario scripted before execution (i.e., with predetermined, fixed actor routes and speeds) may not preserve its intended interaction once the tested ego policy responds in closed loop. Scripted scenarios cannot adapt to unanticipated ego behavior, while learned traffic actors may remain reactive without reliably realizing a particular scenario intent. We introduce a scenario orchestrator that continuously monitors the joint traffic state and adapts non-ego actors through re-timing, re-routing, and role reassignment for creating a specific scenario intent. At each step, the orchestrator solves a constrained optimization problem that preserves the intended interaction while limiting interventions and maintaining traffic feasibility. We further distinguish scenario realization from policy failure, allowing a test to first be judged based on whether the intended interaction occurred and then by how the ego policy responded. Experiments in the CARLA simulator across multiple scenario families and driving policies show that orchestration realizes targeted interactions more reliably than scripted and learned actor-level baselines, particularly under variations in initial conditions and ego behavior. These results support closed-loop scenario orchestration as a tool for controlled and reproducible policy evaluation.
Sources
- OSC2Runner: OpenSCENARIO 2.x Compliant High-Fidelity AV Simulation in CARLA
- Compiling OpenSCENARIO 2.1 for Scenario-Based Testing in CARLA
- ScenePilot: Controllable Boundary-Driven Critical Scenario Generation for Autonomous Driving
- PlanT 2.0: Exposing Biases and Structural Flaws in Closed-Loop Driving
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation