TraversRL: Traversable Pedestrian Pathway Generation With Reinforcement Learning
2026-07-20 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed TraversRL, a new method that creates connected pedestrian pathways from aerial images by simulating how a person might walk through an area. Unlike traditional methods that just label pixels and often produce incomplete maps, TraversRL builds pathways step-by-step, helping it handle tricky cases like partly hidden sidewalks. They showed that their approach makes much more complete and accurate pathway maps than previous methods, by teaching the model to focus both on overall map connectivity and precise details. Using reinforcement learning to improve the final network quality led to fewer mistakes and better navigation graphs.
pedestrian pathwaysaerial imagessegmentationgraph connectivityreinforcement learningpathway extractionIoU (Intersection over Union)visual backbonesnetwork growthgraph-level rewards
Authors
Bin Han, Robert Wolfe, Bill Howe
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.