In Autonomous Driving (AD), detection and tracking of obstacles on the roads is a critical task. Deep-learning based methods using annotated LiDAR data have been the most widely adopted approach for this. Unfortunately, annotating 3D point cloud is a very challenging, time- and money-consuming task. In this letter, we propose a novel LiDAR simulator that augments real point cloud with synthetic obstacles (e.g., vehicles, pedestrians, and other movable objects). Unlike previous simulators that entirely rely on CG (Computer Graphics) models and game engines, our augmented simulator bypasses the requirement to create high-fidelity background CAD (Computer Aided Design) models. Instead, we can deploy a vehicle with a LiDAR scanner to sweep the street of interests to obtain the background points cloud, based on which annotated point cloud can be automatically generated. This 'scan-and-simulate' capability makes our approach scalable and practical, ready for large-scale industrial applications. In this letter, we describe our simulator in detail, in particular the placement of obstacles that is critical for performance enhancement. We show that detectors with our simulated LiDAR point cloud alone can perform comparably (within two percentage points) with these trained with real data. Mixing real and simulated data can achieve over 95% accuracy.
|Number of pages||8|
|Journal||IEEE Robotics and Automation Letters|
|State||Published - Apr 2020|
Bibliographical noteFunding Information:
Manuscript received September 10, 2019; accepted January 8, 2020. Date of publication January 28, 2020; date of current version February 11, 2020. This letter was recommended for publication by Associate Editor A. Faust and Editor N. Amato upon evaluation of the reviewers’ comments. This work of R. Yang was supported by Baidu Research. (Corresponding authors: Jin Fang; Dingfu Zhou.) J. Fang and D. Zhou are with the Baidu Research and National Engineering Laboratory of Deep Learning Technology and Application, Beijing 100000, China (e-mail: firstname.lastname@example.org; email@example.com).
© 2016 IEEE.
- Simulation and animation
- computer vision for automation
- object detection
- segmentation and categorization
ASJC Scopus subject areas
- Control and Systems Engineering
- Biomedical Engineering
- Human-Computer Interaction
- Mechanical Engineering
- Computer Vision and Pattern Recognition
- Computer Science Applications
- Control and Optimization
- Artificial Intelligence