Human-Inspired Neuro-Symbolic World Modeling and Logic Reasoning for Interpretable Safe UAV Landing Site Assessment
Weixian Qian, Tianyi Yang, Sebastian Schroder, Yao Deng, Jiaohong Yao, Xiao Cheng, Richard Han, Xi Zheng
Why It Matters
What makes this one worth your time
This work is relevant for AI engineers and researchers interested in improving the safety and interpretability of UAV operations in unstructured environments, which is crucial for real-world applications.
NeuroSymLand offers interpretable UAV landing site assessment by combining neuro-symbolic modeling with logic reasoning.
Summary
The paper introduces NeuroSymLand, a neuro-symbolic framework for UAV landing site assessment that separates perception-driven world modeling from logic-based safety reasoning, using a lightweight segmentation model and symbolic safety rules for interpretable and efficient decision-making.
Key contributions
- Development of a neuro-symbolic framework for UAV landing site assessment.
- Integration of a lightweight segmentation model with symbolic reasoning for efficient and interpretable decision-making.
- Demonstration of superior performance over competitive baselines in simulated and hardware-in-the-loop scenarios.
Notable insights
- The use of a probabilistic semantic scene graph for encoding objects and spatial relations enhances interpretability.
- Symbolic safety rules synthesized with human-in-the-loop refinement provide transparent decision-making.
Possible limitations
- Not stated in the abstract
Abstract
arXiv:2510.22204v3 Announce Type: replace-cross Abstract: Reliable assessment of safe landing sites in unstructured environments is essential for deploying Unmanned Aerial Vehicles (UAVs) in real-world applications such as delivery, inspection, and surveillance. Existing learning-based approaches often degrade under covariate shift and offer limited transparency, making their decisions difficult to interpret and validate on resource-constrained platforms. We present NeuroSymLand, a neuro-symbolic framework for marker-free UAV landing site safety assessment that explicitly separates perception-driven world modeling from logic-based safety reasoning. A lightweight segmentation model incrementally constructs a probabilistic semantic scene graph encoding objects, attributes, and spatial relations. Symbolic safety rules, synthesized offline via large language models with human-in-the-loop refinement, are executed directly over this world model at runtime to perform white-box reasoning, producing ranked landing candidates with human-readable explanations of the underlying safety constraints. Across 72 simulated and hardware-in-the-loop landing scenarios, NeuroSymLand achieves 61 successful assessments, outperforming four competitive baselines, which achieve between 37 and 57 successes. Qualitative analysis highlights its superior interpretability and transparent reasoning, while deployment incurs negligible edge overhead. Our results suggest that combining explicit world modeling with symbolic reasoning can support accurate, interpretable, and edge-deployable safety assessment in mobile systems, as demonstrated through UAV landing site assessment.