Abstract
Detection of traversable areas is essential to navigation of autonomous personal mobility systems in unknown pedestrian environments. However, traffic rules may recommend or require driving in specified areas, such as sidewalks, in environments where roadways and sidewalks coexist. Therefore, it is necessary for such autonomous mobility systems to estimate the areas that are mechanically traversable and recommended by traffic rules and to navigate based on this estimation. In this paper, we propose a method for weakly-supervised recommended traversable area segmentation in environments with no edges using automatically labeled images based on paths selected by humans. This approach is based on the idea that a human-selected driving path more accurately reflects both mechanical traversability and human understanding of traffic rules and visual information. In addition, we propose a data augmentation method and a loss weighting method for detecting the appropriate recommended traversable area from a single human-selected path. Evaluation of the results showed that the proposed learning methods are effective for recommended traversable area detection and found that weakly-supervised semantic segmentation using human-selected path information is useful for recommended area detection in environments with no edges.
Highlights
In recent years, Mobility on Demand (MoD) services to deploy diverse mobility solutions for different mobility needs have attracted attention [1], aiming at providing last-mile transportation in environments where public transportation is insufficient, as well as to increase accessibility of social spaces and revitalize economic activities by increasing urban mobility
Many autonomous mobility systems have been proposed for pedestrian environments such as sidewalks and community roads, among which many require accurate localization based on map information constructed using sensors such as a laser range finder (LRF)
Some of the learning conditions for the baseline were modified based on the conditions shown in Table 1, assuming that the inference is performed at a speed faster than 10 Hz on an in-vehicle PC (Intel Core i7-8750H CPU 2.2 GHz, 32 GB RAM, Geforce RTX 2060 GPU)
Summary
Mobility on Demand (MoD) services to deploy diverse mobility solutions for different mobility needs have attracted attention [1], aiming at providing last-mile transportation in environments where public transportation is insufficient, as well as to increase accessibility of social spaces and revitalize economic activities by increasing urban mobility Among these services, the realization of autonomous personal mobility systems is expected [1,2]. In an environment where the roadway and sidewalk coexist, it is necessary to estimate a driving area that is both mechanically traversable and recommended by traffic rules and to navigate based on this estimation. The area where the terrain is mechanically traversable and driving is recommended by traffic rules is defined as the recommended traversable area, and the degree of the recommendation is defined as driving recommendation degree
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.