Effective Free-Driving Region Detection for Mobile Robots by Uncertainty Estimation Using RGB-D Data
Open Access
Abstract
Accurate segmentation of drivable areas and road obstacles is critical for autonomous mobile robots to navigate safely in indoor and outdoor environments. With the fast advancement of deep learning, mobile robots may now perform autonomous navigation based on what they learned in the learning phase. On the other hand, existing techniques often have low performance when confronted with complex situations since unfamiliar objects are not included in the training dataset. Additionally, the use of a large amount of labeled data is generally essential for training deep neural networks to achieve good performance, which is time-consuming and labor-intensive. Thus, this paper presents a solution to these issues by proposing a self-supervised learning method for the drivable areas and road anomaly segmentation. First, we propose the Automatic Generating Segmentation Label (AGSL) framework, which is an efficient system automatically generating segmentation labels for drivable areas and road anomalies by finding dissimilarities between the input and resynthesized image and localizing obstacles in the disparity map. Then, we train RGB-D datasets with a semantic segmentation network using self-generated ground truth labels derived from our method (AGSL labels) to get the pre-trained model. The results showed that our AGSL achieved high performance in labeling evaluation, and the pre-trained model also obtains certain confidence in real-time segmentation application on mobile robots.Keywords
Funding Information
- Ministry of Science and Technology (MOST 109-2221-E-011-112-MY3)
This publication has 24 references indexed in Scilit:
- ICNet for Real-Time Semantic Segmentation on High-Resolution Images2018
- A Co-Point Mapping-Based Approach to Drivable Area Detection for Self-Driving CarsEngineering, 2018
- Photographic Image Synthesis with Cascaded Refinement Networks2017
- Pyramid Scene Parsing Network2017
- FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-Based CNN Architecture2017
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016
- Complex ground plane detection based on V-disparity map in off-road environment2013
- U-V-Disparity based Obstacle Detection with 3D Camera and steerable filter2011
- ImageNet: A large-scale hierarchical image database2009
- Generalizing the Hough transform to detect arbitrary shapesPattern Recognition, 1981