# iCurb: Imitation Learning-based Detection of Road Curbs using Aerial Images for Autonomous Driving

arXiv: https://arxiv.org/abs/2103.17118 · HTML: https://mlsanity.com/paper/2103.17118/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in End-to-end system architecture, one of 9 directions in End-to-end autonomous driving.
- Builds on 13 of its 27 references that are in the map.
- First posted on arXiv 31 Mar 2021.

## Placed in

- End-to-end autonomous driving / [End-to-end system architecture](https://mlsanity.com/driving/end-to-end-system-architecture/)

## Builds on (most cited first, 13 of 13)

- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [Reinforcement and Imitation Learning for Diverse Visuomotor Skills](https://mlsanity.com/paper/1802.09564/) (2018)
- [Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++](https://mlsanity.com/paper/1803.09693/) (2018)
- [RoadTracer: Automatic Extraction of Road Networks from Aerial Images](https://mlsanity.com/paper/1802.03680/) (2018)
- [Annotating Object Instances with a Polygon-RNN](https://mlsanity.com/paper/1704.05548/) (2017)
- [Topological Map Extraction from Overhead Images](https://mlsanity.com/paper/1812.01497/) (2018)
- [DAGMapper: Learning to Map by Discovering Lane Topology](https://mlsanity.com/paper/2012.12377/) (2020)
- [Hierarchical Recurrent Attention Networks for Structured Online Maps](https://mlsanity.com/paper/2012.12314/) (2020)
- [Convolutional Recurrent Network for Road Boundary Extraction](https://mlsanity.com/paper/2012.12160/) (2020)
- [Image-Conditioned Graph Generation for Road Network Extraction](https://mlsanity.com/paper/1910.14388/) (2019)
- [Road Curb Detection and Localization with Monocular Forward-view Vehicle Camera](https://mlsanity.com/paper/2002.12492/) (2020)
- [Metric-Based Imitation Learning Between Two Dissimilar Anthropomorphic Robotic Arms](https://mlsanity.com/paper/2003.02638/) (2020)

## Built on by (most cited first, 21 of 21)

- [Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction](https://mlsanity.com/paper/2303.08815/) (2023)
- [RNGDet: Road Network Graph Detection by Transformer in Aerial Images](https://mlsanity.com/paper/2202.07824/) (2022)
- [RNGDet++: Road Network Graph Detection by Transformer with Instance Segmentation and Multi-scale Features Enhancement](https://mlsanity.com/paper/2209.10150/) (2022)
- [Structure-Aware Image Segmentation with Homotopy Warping](https://mlsanity.com/paper/2112.07812/) (2021)
- [InsMapper: Exploring Inner-instance Information for Vectorized HD Mapping](https://mlsanity.com/paper/2308.08543/) (2023)
- [SPIN Road Mapper: Extracting Roads from Aerial Images via Spatial and Interaction Space Graph Reasoning for Autonomous Driving](https://mlsanity.com/paper/2109.07701/) (2021)
- [CenterLineDet: CenterLine Graph Detection for Road Lanes with Vehicle-mounted Sensors by Transformer for HD Map Generation](https://mlsanity.com/paper/2209.07734/) (2022)
- [Building Lane-Level Maps from Aerial Images](https://mlsanity.com/paper/2312.13449/) (2023)
- [csBoundary: City-scale Road-boundary Detection in Aerial Images for High-definition Maps](https://mlsanity.com/paper/2111.06020/) (2021)
- [VMA: Divide-and-Conquer Vectorized Map Annotation System for Large-Scale Driving Scene](https://mlsanity.com/paper/2304.09807/) (2023)
- [CP-loss: Connectivity-preserving Loss for Road Curb Detection in Autonomous Driving with Aerial Images](https://mlsanity.com/paper/2107.11920/) (2021)
- [Patched Line Segment Learning for Vector Road Mapping](https://mlsanity.com/paper/2309.02923/) (2023)
- [CurbNet: Curb Detection Framework Based on LiDAR Point Cloud Segmentation](https://mlsanity.com/paper/2403.16794/) (2024)
- [LDPoly: Latent Diffusion for Polygonal Road Outline Extraction in Large-Scale Topographic Mapping](https://mlsanity.com/paper/2504.20645/) (2025)
- [Towards Defensive Autonomous Driving: Collecting and Probing Driving Demonstrations of Mixed Qualities](https://mlsanity.com/paper/2109.07995/) (2021)
- [A Concise Survey on Lane Topology Reasoning for HD Mapping](https://mlsanity.com/paper/2504.01989/) (2025)
- [Leveraging GNSS and Onboard Visual Data from Consumer Vehicles for Robust Road Network Estimation](https://mlsanity.com/paper/2408.01640/) (2024)
- [TreeFormer: Single-view Plant Skeleton Estimation via Tree-constrained Graph Generation](https://mlsanity.com/paper/2411.16132/) (2024)
- [InVDriver: Intra-Instance Aware Vectorized Query-Based Autonomous Driving Transformer](https://mlsanity.com/paper/2502.17949/) (2025)
- [UniVector: Unified Vector Extraction via Instance-Geometry Interaction](https://mlsanity.com/paper/2510.13234/) (2025)
- [Correcting Learning-based Perception for Safety](https://mlsanity.com/paper/2609.22108/) (2026)

## Abstract (arXiv)

Detection of road curbs is an essential capability for autonomous driving. It can be used for autonomous vehicles to determine drivable areas on roads. Usually, road curbs are detected on-line using vehicle-mounted sensors, such as video cameras and 3-D Lidars. However, on-line detection using video cameras may suffer from challenging illumination conditions, and Lidar-based approaches may be difficult to detect far-away road curbs due to the sparsity issue of point clouds. In recent years, aerial images are becoming more and more worldwide available. We find that the visual appearances between road areas and off-road areas are usually different in aerial images, so we propose a novel solution to detect road curbs off-line using aerial images. The input to our method is an aerial image, and the output is directly a graph (i.e., vertices and edges) representing road curbs. To this end, we formulate the problem as an imitation learning problem, and design a novel network and an innovative training strategy to train an agent to iteratively find the road-curb graph. The experimental results on a public dataset confirm the effectiveness and superiority of our method. This work is accompanied with a demonstration video and a supplementary document at https://tonyxuqaq.github.io/iCurb/.