cs.RONov 8, 2026

ScanDreamer: A Map-Grounded World Model for Quadrotor Navigation

Authors: Yunyi Gao, Yixing Shi, Yize Liu, Hai-Duong Tran, Nhat-Hoang P. Nguyen, Shuai Wang, Yi Deng, Shengming Liu, 

Organizations: School of Artificial Intelligence and Robotics, Xiamen University Malaysia, Malaysia · Center for AI Research, VinUniversity, Hanoi, Vietnam · Air Traffic Management Research Institute, Nanyang Technological University, Singapore

Abstract

Quadrotors inspecting buildings and tunnels must navigate unknown clutter with a forward-facing depth camera whose limited field of view constrains scene understanding and collision-avoiding navigation. Recent world-model agents learn navigation through imagined experience (e.g., AirDreamer), but remain data-intensive and often lack explicit geometric memory and awareness of what the camera can observe. We propose ScanDreamer, a map-grounded world model that constructs an online 2D scan-memory map from depth images and vehicle pose. Our world model, actor, and critic are conditioned on this map, which also defines a geodesic progress reward. Moreover, a forward-cone penalty discourages horizontal motion outside the camera's viewing direction. During imagination, ScanDreamer propagates the quadrotor pose over a frozen map and derives progress and wall-contact signals from the mapped geometry. We train ScanDreamer for 0.8 million environment steps (5.5 h on one GPU) and evaluate it in NVIDIA Isaac Sim over 1560 episodes spanning unseen layouts and parameter ranges. Across three seeds (mean ±\pm SD), ScanDreamer achieves 96.3 ±\pm 0.3% success with 3.6 ±\pm 0.3% collision, compared with 59.6 ±\pm 3.0% success and 28.8 ±\pm 2.8% collision for AirDreamer at the same online-interaction budget. Removing the forward-cone penalty increases collisions to 9.9 ±\pm 3.1%. These results show that combining explicit map memory, map-grounded imagination, and perception-aware motion substantially improves navigation performance and data efficiency. The source code is available at https://github.com/WANGSHUAIzzzz/ScanDreamer.

Figures & tables

Explore similar work

CardsList
  1. MAD: Mapping-Aware World Models for Agile Quadrotor Flight

    Jun 3, 2026Xinhong Zhang, Runqing Wang, Yunfan Ren +6Robot Policy LearningWorld Models for Robotics

  2. AirDreamer: Generalist Drone Navigation with World Models

    Jun 2, 2026Zian Liu, Andong Yang, Chunkai Yang +3RL for RoboticsWorld Models for Robotics

  3. Flying on Imagination: DreamerV3-Style World Models under Environment Distribution Shift for Quadrotor Navigation

    Jun 3, 2026Luca Zanatta, Grzegorz Malczyk, Kostas AlexisWorld Models for RoboticsWorld Models