[2509.23589] BridgeDrive: Diffusion Bridge Policy for Closed-Loop Trajectory Planning in Autonomous Driving

Computer Science > Artificial Intelligence arXiv:2509.23589 (cs) [Submitted on 28 Sep 2025 (v1), last revised 2 Mar 2026 (this version, v3)] Title:BridgeDrive: Diffusion Bridge Policy for Closed-Loop Trajectory Planning in Autonomous Driving Authors:Shu Liu, Wenlin Chen, Weihao Li, Zheng Wang, Lijin Yang, Jianing Huang, Yipin Zhang, Zhongzhan Huang, Ze Cheng, Hao Yang View a PDF of the paper titled BridgeDrive: Diffusion Bridge Policy for Closed-Loop Trajectory Planning in Autonomous Driving, by Shu Liu and 9 other authors View PDF HTML (experimental) Abstract:Diffusion-based planners have shown strong potential for autonomous driving by capturing multi-modal driving behaviors. A key challenge is how to effectively guide these models for safe and reactive planning in closed-loop settings, where the ego vehicle's actions influence future states. Recent work leverages typical expert driving behaviors (i.e., anchors) to guide diffusion planners but relies on a truncated diffusion schedule that introduces an asymmetry between the forward and denoising processes, diverging from the core principles of diffusion models. To address this, we introduce BridgeDrive, a novel anchor-guided diffusion bridge policy for closed-loop trajectory planning. Our approach formulates planning as a diffusion bridge that directly transforms coarse anchor trajectories into refined, context-aware plans, ensuring theoretical consistency between the forward and reverse processes. BridgeDrive is compati...