Topoenhance improves lane and traffic connectivity for autonomous driving
Refine Connections, Close the Gap: A Reliable Enhancement Framework for Driving Scene Topology
Computer Vision and Pattern Recognition
Summary
Self-driving cars need to understand how lanes and traffic features connect to navigate safely. Current methods detect these parts well but struggle to figure out how they connect reliably. The authors propose TopoEnhance, a framework that fixes errors and inconsistencies in these connections by learning from examples where some connections are randomly corrupted. This makes the final maps much more accurate and dependable for the car's decision-making.
What this means in practice
- •For autonomous vehicle engineers: Improve road network maps with reliable connection info to enhance self-driving car path planning and control.
- •For urban traffic planners: More accurate connectivity maps can support simulation and planning tools for traffic management and infrastructure design.
Authors
Xiaoqi Wang, Dingyi Zhaung, David Paz, Wenbin He, Yucai Bai, Peng Zhou, Rui Zhang, Jinhua Zhao, Liu Ren
Abstract
In autonomous driving, understanding scene topology - the connectivity between lanes and traffic elements - is critical for safe path planning and motion control. While current methods excel at detecting individual map elements, their connectivity reasoning often falls short of its theoretical potential, leaving a significant performance gap relative to the theoretical upper-bound achievable given the underlying detections. Furthermore, the decision-ready topology graphs passed to downstream tasks often remain unreliable. Current approaches typically derive connectivity by thresholding continuous topology scores; however, these scores often fail to reflect the true logical likelihood of connectivity, resulting in false positives or missing connections. Existing benchmarks further overlook this issue by primarily evaluating continuous metrics, rather than assessing the discrete connectivity required for decision-making. To bridge these gaps, we propose TopoEnhance, a novel topology enhancement framework designed to unlock the latent potential of existing methods and improve the reliability of decision-ready topology. We formulate topology enhancement as a denoising-based reconstruction process, where the model learns to recover structural consistency from stochastically corrupted ground-truth graphs. This formulation enables the model to resolve logical inconsistencies and rectify unreliable connections, producing robust discrete topology graphs that closely approach theoretical maximum performance. Extensive experiments across different baselines show that TopoEnhance consistently improves both continuous topology metrics (TOP score), and discrete connectivity measured by our adapted Topology Jaccard Similarity (TJS) metric. As a flexible, source-agnostic framework, TopoEnhance delivers substantial gains across diverse state-of-the-art baselines without requiring retraining.