Map-World: Masked Action planning and Path-Integral World Model for Autonomous Driving

Bin Hu, Zijian Lu, Haicheng Liao, Chengran Yuan, Bin Rao, Yongkang Li, Guofa Li, Zhiyong Cui, Chengzhong Xu, Zhenning LiarXiv 2025 · DOI · arXiv

Abstract

Autonomous driving requires navigating complex environments where multiple plausible future trajectories exist. Traditional end-to-end systems often rely on predefined trajectory anchors, which can be computationally expensive or lack the flexibility to handle diverse road geometries. This paper introduces Map-World, a prior-free planning framework that utilizes Masked Action Planning (MAP) to treat future motion as a sequence completion task. Combined with a Path-Integral World Model, Map-World learns from a full distribution of potential futures rather than a single "best" path. The proposed method achieves state-of-the-art results on the NAVSIM benchmark with a PDMS score of 88.8 and maintains real-time inference speeds.

Introduction

A critical challenge in autonomous driving is handling multi-modality—the fact that multiple safe paths may exist at any given moment (e.g., turning left vs. going straight). Most current models address this by selecting from a fixed library of "anchors." However, anchors present a trade-off: a small set may fail in complex geometries, while a large set increases computational overhead. Furthermore, many systems discard alternative safe trajectories during training, losing valuable information. Map-World addresses these issues by replacing handcrafted anchors with a generative approach that understands the entire spectrum of possible outcomes.

Methods

Map-World introduces two primary innovations: Masked Action Planning and a Path-Integral World Model.

Masked Action Planning (MAP)

Inspired by Masked Autoencoders, MAP treats trajectory planning as a sequence completion task. The model processes past states and a coarse driving intention, then uses a Transformer decoder to reconstruct "masked" future waypoints. By injecting noise into a compact latent state, the system generates diverse and temporally consistent trajectories without requiring a predefined anchor library.

Path-Integral World Model

Rather than evaluating a single chosen path, Map-World employs a lightweight world model to simulate future Bird's Eye View (BEV) semantics for all candidate trajectories. Using a differentiable path-weighting scheme inspired by Feynman’s path-integral formulation, the training loss is calculated as an expectation over all generated modes. This allows the planner to learn from the entire distribution of plausible futures in a fully differentiable manner.

The Map-World pipeline (a) and the detailed architecture of the End-to-End Network (b), showing the Masked Action and Trajectory Decoder components.

Experiments and Results

The framework was evaluated on the NAVSIM and nuScenes datasets.

Performance on Benchmarks

Map-World sets a new state-of-the-art on the NAVSIM benchmark, achieving a PDMS score of 88.8, outperforming existing models like DiffusionDrive. On the nuScenes validation set, it achieved a remarkably low average L2 error of 0.50m and a collision rate of 0.07%, demonstrating superior safety and precision compared to anchor-based methods.

Efficiency and Qualitative Analysis

Despite its multi-modal nature, Map-World is highly efficient, with an inference latency of 13.5 ms on an NVIDIA 4090. Qualitative results show that the model generates trajectories that align more closely with ground-truth human driving, particularly in complex intersections where baseline models often struggle.

Qualitative comparison between Map-World (Ours) and the WoTE baseline across various driving scenarios. Map-World trajectories (blue) consistently align better with ground truth (green) than the baseline (orange).

Conclusion

Map-World demonstrates that a prior-free, generative approach to trajectory planning can outperform traditional anchor-based systems. By leveraging masked sequence completion and path-integral weighting, the model achieves robust, safe, and efficient autonomous driving. Future work will explore scene-adaptive mode allocation to dynamically adjust the number of predicted paths based on environmental complexity.

Summary updated

Abstract

Motion planning for autonomous driving must handle multiple plausible futures while remaining computationally efficient. Recent end-to-end systems and world-model-based planners predict rich multi-modal trajectories, but typically rely on handcrafted anchors or reinforcement learning to select a single best mode for training and control. This selection discards information about alternative futures and complicates optimization. We propose MAP-World, a prior-free multi-modal planning framework that couples masked action planning with a path-weighted world model. The Masked Action Planning (MAP) module treats future ego motion as masked sequence completion: past waypoints are encoded as visible tokens, future waypoints are represented as mask tokens, and a driving-intent path provides a coarse scaffold. A compact latent planning state is expanded into multiple trajectory queries with injected noise, yielding diverse, temporally consistent modes without anchor libraries or teacher policies. A lightweight world model then rolls out future BEV semantics conditioned on each candidate trajectory. During training, semantic losses are computed as an expectation over modes, using trajectory probabilities as discrete path weights, so the planner learns from the full distribution of plausible futures instead of a single selected path. On NAVSIM, our method matches anchor-based approaches and achieves state-of-the-art performance among world-model-based methods, while avoiding reinforcement learning and maintaining real-time inference latency.
BibTeX
@misc{hu2025map,
  author = {Bin Hu and Zijian Lu and Haicheng Liao and Chengran Yuan and Bin Rao and Yongkang Li and Guofa Li and Zhiyong Cui and Chengzhong Xu and Zhenning Li},
  title = {{Map-World: Masked Action planning and Path-Integral World Model for Autonomous Driving}},
  year = {2025},
  eprint = {2511.20156},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.20156},
}
Figure