SafeLand: Safe Autonomous Landing in Unknown Environments with Bayesian Semantic Mapping

• URL: http://arxiv.org/abs/2603.17430v1
• Date: Wed, 18 Mar 2026 07:11:54 GMT
• Title: SafeLand: Safe Autonomous Landing in Unknown Environments with Bayesian Semantic Mapping
• Abstract summary: We introduce SafeLand, a vision-based system for safe autonomous landing (SAL)<n>Our approach constructs an online semantic ground map via deep learning-based semantic segmentation, optimized for embedded deployment.<n>We extensively evaluate our method in 200 simulations and 60 end-to-end field tests across industrial, urban, and rural environments at altitudes up to 100m.
• Score: 41.90149506430796
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Autonomous landing of uncrewed aerial vehicles (UAVs) in unknown, dynamic environments poses significant safety challenges, particularly near people and infrastructure, as UAVs transition to routine urban and rural operations. Existing methods often rely on prior maps, heavy sensors like LiDAR, static markers, or fail to handle non-cooperative dynamic obstacles like humans, limiting generalization and real-time performance. To address these challenges, we introduce SafeLand, a lean, vision-based system for safe autonomous landing (SAL) that requires no prior information and operates only with a camera and a lightweight height sensor. Our approach constructs an online semantic ground map via deep learning-based semantic segmentation, optimized for embedded deployment and trained on a consolidation of seven curated public aerial datasets (achieving 70.22% mIoU across 20 classes), which is further refined through Bayesian probabilistic filtering with temporal semantic decay to robustly identify metric-scale landing spots. A behavior tree then governs adaptive landing, iteratively validates the spot, and reacts in real time to dynamic obstacles by pausing, climbing, or rerouting to alternative spots, maximizing human safety. We extensively evaluate our method in 200 simulations and 60 end-to-end field tests across industrial, urban, and rural environments at altitudes up to 100m, demonstrating zero false negatives for human detection. Compared to the state of the art, SafeLand achieves sub-second response latency, substantially lower than previous methods, while maintaining a superior success rate of 95%. To facilitate further research in aerial robotics, we release SafeLand's segmentation model as a plug-and-play ROS package, available at https://github.com/markus-42/SafeLand.

Related papers

• DESCENT: Directed Edge Scene Encoding for Airport Surface Movement Prediction [54.94692733670454]
  DESCENT is a transformer-based architecture designed to handle heterogeneous dynamics and strict topological constraints.<n>Our approach features a Potential Reachable Set (PRS) context sampling mechanism that adaptively collects airfield environment context.<n>Our evaluations on the Amelia-10 benchmark demonstrate significant performance improvements over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-08-26T16:49:50Z)
• Synthetic-to-Real Pipeline for Safe Landing Zone Detection [0.0]
  This work proposes a comprehensive perception and data generation pipeline designed to bridge the sim-to-real gap for autonomous landing tasks.<n>We introduce a procedural synthetic data engine that generates urban environments with automated semantic annotations through domain randomization.<n>A deterministic landing module utilizes a Euclidean Distance Transform (EDT) and dynamic inference logic to identify the largest inscribed safe landing zones.
  arXiv  Detail & Related papers  (2026-06-09T01:32:07Z)
• Meridian: Metric-Semantic Primitive Matching for Cross-View Geo-Localization Beyond Urban Environments [47.53030013880309]
  Successful robot automation requires accurate global localization to support repeatability, task planning, goal specification, and safe operation.<n>We present Meridian, a method for matching high-level metric-semantic primitives across aerial images and ground robot RGB-D camera data.<n>We demonstrate that our algorithm can localize a ground robot across a wide variety of environments, including an autonomous driving dataset, a park and campus area, and a wilderness camp.
  arXiv  Detail & Related papers  (2026-06-04T15:52:40Z)
• Semantically Aware UAV Landing Site Assessment from Remote Sensing Imagery via Multimodal Large Language Models [5.987458168544856]
  Safe UAV emergency landing requires understanding complex semantic risks invisible to traditional geometric sensors.<n>We propose a novel framework leveraging Remote Sensing (RS) imagery and Multimodal Large Language Models (MLLMs) for context-aware landing site assessment.
  arXiv  Detail & Related papers  (2026-02-01T11:30:03Z)
• NOVA: Navigation via Object-Centric Visual Autonomy for High-Speed Target Tracking in Unstructured GPS-Denied Environments [56.35569661650558]
  We introduce NOVA, a fully onboard, object-centric framework that enables robust target tracking and collision-aware navigation.<n>Rather than constructing a global map, NOVA formulates perception, estimation, and control entirely in the target's reference frame.<n>We validate NOVA across challenging real-world scenarios, including urban mazes, forest trails, and repeated transitions through buildings with intermittent GPS loss.
  arXiv  Detail & Related papers  (2025-06-23T14:28:30Z)
• Secure Navigation using Landmark-based Localization in a GPS-denied Environment [1.19658449368018]
  This paper proposes a novel framework that integrates landmark-based localization (LanBLoc) with an Extended Kalman Filter (EKF) to predict the future state of moving entities along the battlefield. We present a simulated battlefield scenario for two different approaches that guide a moving entity through an obstacle and hazard-free path.
  arXiv  Detail & Related papers  (2024-02-22T04:41:56Z)
• VAPOR: Legged Robot Navigation in Outdoor Vegetation Using Offline Reinforcement Learning [53.13393315664145]
  We present VAPOR, a novel method for autonomous legged robot navigation in unstructured, densely vegetated outdoor environments. Our method trains a novel RL policy using an actor-critic network and arbitrary data collected in real outdoor vegetation. We observe that VAPOR's actions improve success rates by up to 40%, decrease the average current consumption by up to 2.9%, and decrease the normalized trajectory length by up to 11.2%.
  arXiv  Detail & Related papers  (2023-09-14T16:21:27Z)
• You Only Crash Once: Improved Object Detection for Real-Time, Sim-to-Real Hazardous Terrain Detection and Classification for Autonomous Planetary Landings [7.201292864036088]
  A cheap and effective way of detecting hazardous terrain is through the use of visual cameras. Traditional techniques for visual hazardous terrain detection focus on template matching and registration to pre-built hazard maps. We introduce You Only Crash Once (YOCO), a deep learning-based visual hazardous terrain detection and classification technique.
  arXiv  Detail & Related papers  (2023-03-08T21:11:51Z)
• Incremental 3D Scene Completion for Safe and Efficient Exploration Mapping and Planning [60.599223456298915]
  We propose a novel way to integrate deep learning into exploration by leveraging 3D scene completion for informed, safe, and interpretable mapping and planning. We show that our method can speed up coverage of an environment by 73% compared to the baselines with only minimal reduction in map accuracy. Even if scene completions are not included in the final map, we show that they can be used to guide the robot to choose more informative paths, speeding up the measurement of the scene with the robot's sensors by 35%.
  arXiv  Detail & Related papers  (2022-08-17T14:19:33Z)
• Visual-based Safe Landing for UAVs in Populated Areas: Real-time Validation in Virtual Environments [0.0]
  We propose a framework for real-time safe and thorough evaluation of vision-based autonomous landing in populated scenarios. We propose to use the Unreal graphics engine coupled with the AirSim plugin for drone's simulation. We study two different criteria for selecting the "best" SLZ, and evaluate them during autonomous landing of a virtual drone in different scenarios.
  arXiv  Detail & Related papers  (2022-03-25T17:22:24Z)
• Embedding Earth: Self-supervised contrastive pre-training for dense land cover classification [61.44538721707377]
  We present Embedding Earth a self-supervised contrastive pre-training method for leveraging the large availability of satellite imagery. We observe significant improvements up to 25% absolute mIoU when pre-trained with our proposed method. We find that learnt features can generalize between disparate regions opening up the possibility of using the proposed pre-training scheme.
  arXiv  Detail & Related papers  (2022-03-11T16:14:14Z)
• Robust Autonomous Landing of UAV in Non-Cooperative Environments based on Dynamic Time Camera-LiDAR Fusion [11.407952542799526]
  We construct a UAV system equipped with low-cost LiDAR and binocular cameras to realize autonomous landing in non-cooperative environments. Taking advantage of the non-repetitive scanning and high FOV coverage characteristics of LiDAR, we come up with a dynamic time depth completion algorithm. Based on the depth map, the high-level terrain information such as slope, roughness, and the size of the safe area are derived.
  arXiv  Detail & Related papers  (2020-11-27T14:47:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.