IEEE Transactions on Intelligent Transportation Systems 2021
Pengdi Huang1 Liqiang Lin1 Kai Xu2 Hui Huang1*
1Shenzhen University 2National University of Defense Technology
Fig. 1. A mobile robot is autonomously exploring and scanning an unseen outdoor scene. The path (yellow curve in (a)) is planned and optimized on-the-fly, while the scans are incrementally aggregated. The final point cloud in (b) plots the scanning confidence (red is confident) over the ground.
Abstract
Autonomous 3D acquisition of outdoor environments poses special challenges. Different from indoor scenes, where the room space is delineated by clear boundaries and separations (e.g., walls and furniture), an outdoor environment is spacious and unbounded (thinking of a campus). Therefore, unlike for indoor scenes where the scanning effort is mainly devoted to the discovery of boundary surfaces, scanning an open and unbounded area requires actively delimiting the extent of scanning region and dynamically planning a traverse path within that region. Thus, for outdoor scenes, we formulate the planning of an energyefficient autonomous scanning through a discrete-continuous optimization of robot scanning paths. The discrete optimization computes a topological map, through solving an online traveling sales problem (Online TSP), which determines the scanning goals and paths on-the-fly. The dynamic goals are determined as a collection of visit sites with high reward of visibility-tounknown. A visit graph is constructed via connecting the visit sites with edges weighted by traversing cost. This topological map evolves as the robot scans via deleting outdated sites that are either visited or become rewardless and inserting newly discovered ones. The continuous part optimizes the traverse paths geometrically between two neighboring visit sites via maximizing the information gain of scanning along the paths. The discrete and continuous processes alternate until the traverse cost of the current graph exceeds the remaining energy capacity of the robot. Our approach is evaluated with both synthetic and field tests, demonstrating its effectiveness and advantages over alternatives.
Fig. 2. An overview of proposed method.
Fig. 10. A gallery of scanned point clouds and online planned scanning paths over eight large synthetic outdoor scenes.
Fig. 11. A gallery of scanned point clouds and online planned scanning paths over six real-world outdoor scenes.
Fig. 17. Comparing the coverage rate in auto-scanning S-scene 3 by our method, frontier exploration, random walk and Fermat spiral coverage. The scanned point clouds and traverse paths for each method are shown in right.
Fig. 18. Demonstrating the progressive scanning of S-scene 2 (top) and S-scene 3 (bottom) by our system, with a series of snapshots of acquired point clouds. Over each point cloud, we plot the color-coded scanning confidence, the visit sites and the planned paths.
Data & Code
Note that the DATA and CODE are free for Research and Education Use ONLY.
Please cite our paper (add the bibtex below) if you use any part of our ALGORITHM, CODE, DATA or RESULTS in any publication.
Bibtex
@article{Husky,
title = {Autonomous Outdoor Scanning via Online Topological and Geometric Path Optimization},
author = {Pengdi Huang and Liqiang Lin and Kai Xu and Hui Huang},
journal = {IEEE Transactions on Intelligent Transportation Systems},
volume = {},
number = {},
pages = {},
year = {2021},
}