ACT-Bench: Towards Action Controllable World Models for Autonomous Driving
This work addresses a gap in reproducible evaluation for action-controllable world models in autonomous driving, though it is incremental as it builds on existing world model research.
The paper tackles the problem of evaluating action fidelity in world models for autonomous driving, which is crucial for generating targeted simulation scenes, and introduces ACT-Bench, an open-access framework with a baseline model Terra that shows improved action fidelity over state-of-the-art models.
World models have emerged as promising neural simulators for autonomous driving, with the potential to supplement scarce real-world data and enable closed-loop evaluations. However, current research primarily evaluates these models based on visual realism or downstream task performance, with limited focus on fidelity to specific action instructions - a crucial property for generating targeted simulation scenes. Although some studies address action fidelity, their evaluations rely on closed-source mechanisms, limiting reproducibility. To address this gap, we develop an open-access evaluation framework, ACT-Bench, for quantifying action fidelity, along with a baseline world model, Terra. Our benchmarking framework includes a large-scale dataset pairing short context videos from nuScenes with corresponding future trajectory data, which provides conditional input for generating future video frames and enables evaluation of action fidelity for executed motions. Furthermore, Terra is trained on multiple large-scale trajectory-annotated datasets to enhance action fidelity. Leveraging this framework, we demonstrate that the state-of-the-art model does not fully adhere to given instructions, while Terra achieves improved action fidelity. All components of our benchmark framework will be made publicly available to support future research.