UniDrive-WM: Unified Understanding, Planning and Generation World Model For Autonomous Driving
This work addresses the challenge of safe and efficient autonomous driving by tightly integrating perception, prediction, and planning, representing a novel approach rather than an incremental improvement.
The paper tackles the problem of autonomous driving by proposing UniDrive-WM, a unified world model that integrates scene understanding, trajectory planning, and future image generation, resulting in a 5.9% improvement in L2 trajectory error and a 9.2% reduction in collision rate over previous methods on the Bench2Drive benchmark.
World models have become central to autonomous driving, where accurate scene understanding and future prediction are crucial for safe control. Recent work has explored using vision-language models (VLMs) for planning, yet existing approaches typically treat perception, prediction, and planning as separate modules. We propose UniDrive-WM, a unified VLM-based world model that jointly performs driving-scene understanding, trajectory planning, and trajectory-conditioned future image generation within a single architecture. UniDrive-WM's trajectory planner predicts a future trajectory, which conditions a VLM-based image generator to produce plausible future frames. These predictions provide additional supervisory signals that enhance scene understanding and iteratively refine trajectory generation. We further compare discrete and continuous output representations for future image prediction, analyzing their influence on downstream driving performance. Experiments on the challenging Bench2Drive benchmark show that UniDrive-WM produces high-fidelity future images and improves planning performance by 5.9% in L2 trajectory error and 9.2% in collision rate over the previous best method. These results demonstrate the advantages of tightly integrating VLM-driven reasoning, planning, and generative world modeling for autonomous driving. The project page is available at https://unidrive-wm.github.io/UniDrive-WM .