TraversRL: Traversable Pedestrian Pathway Generation With Reinforcement Learning

2026-07-19

AI Summary

Existing methods for generating pedestrian path networks from aerial imagery often produce fragmented or disconnected graph structures, which hinder reliable navigation. This work addresses this limitation by introducing, for the first time, a traveler-centric perspective that formulates path generation as a vision-guided sequential decision-making process. We propose a reinforcement learning–based iterative generation framework featuring a hybrid action space for short- and long-range directional choices, integration of multi-scale visual features, and a joint reward mechanism operating at both step and graph levels to simultaneously optimize topological connectivity and geometric fidelity. Evaluated on three benchmark datasets, our approach substantially outperforms existing segmentation-based methods, achieving significantly higher buffer IoU scores and more than doubling connectivity metrics, while producing smoother, more coherent paths with fewer spurious branches.

Abstract

Automatically generating pedestrian pathways from aerial images requires producing a connected network suitable for routing, not just detecting where sidewalks appear. Sidewalks and crossings, in contrast to roads, may be partially occluded, implicitly defined, and exhibit complex connectivity patterns. Existing segmentation-based approaches focus on labeling pixels to infer segments, but often produce disconnected or fragmentary graphs that are unreliable for navigation. We introduce TraversRL, a vision-conditioned model that iteratively grows a pathway network from an aerial image, simulating a traveler navigating the built environment. TraversRL uses an action space of short and long direction-distance segments designed to adapt to complex patterns and span occlusions, and uses a combination of graph-level and step-wise rewards to balance overall connectivity with precise edge placement. Across three visual backbones and three intersection datasets, TraversRL substantially improves buffered IoU with the ground-truth graph relative to a state-of-the-art segmentation baseline, and more than doubles metrics of connectivity. Moreover, combining global and local rewards produces cleaner graphs with fewer spurious branches while further improving overall performance. These results demonstrate that modeling pathway extraction as a sequential decision process from the perspective of a traveler, while optimizing for final graph quality with reinforcement learning, produces significantly more reliable pedestrian networks.

Problem

• pedestrian pathway generation
• traversable network
• aerial image analysis
• graph connectivity
• occlusion handling

Innovation

• reinforcement learning
• pathway generation
• graph connectivity
• vision-conditioned navigation
• pedestrian network