A Concept for an Automated Approach of Public Transport Vehicles to a Bus Stop

Abstract

This paper discusses the current methods for vehicle self-localization and compares previous findings to the use for urban public traffic vehicles. In specific, requirements for autonomous buses approaching a bus stop are defined. An autonomous system capable of reliable vehicle self-localization running in real-time in a city scenario shall be developed in a future work based on this paper. The comparison of filter-based estimation and graph-based optimization techniques shows that the latter suits the the automated approach to a bus stop in an urban environment the best. Based on these findings, a concept for self-localization of public transport vehicles equipped with a variety of imaging sensors with the help of a digital high definition map is presented. A current method is shown and a concept of improving the localization by inferring semantic information into landmark detection by low-level data fusion is provided. Validation and verification of the proposed fusion approach have to be carried out in the future, but a validation scenario is presented in this work.

Concept on Landmark Detection in Road Scene Images Taken From a Top-View Camera System

“…In contrast to their methods, we are using the top-view camera system as an additional sensor for vehicle self-localization. In (Albrecht et al, 2019), we proposed a concept on low-level sensor data fusion as a combination of semantic labels from camera images and a laser point cloud. The concept is shown in Figure 4 and extended by the inputs of our novel top-view camera system.…”

“…Concept on vehicle self-localization with low-level data fusion of camera and laser scanner data extended by the presented top-view system. The base of this method is given in (Albrecht et al, 2019), our novel impact is highlighted in gray. markings and curbs in close proximity to the city bus.…”

“…The found lane markings will be used for self-localization in future work, so a relative accuracy of about 10 cm will be needed according to (Albrecht et al, 2019). As stated above, the accuracy of objects will be evaluated with the originally presented top-view system mounted on the test bus.…”

“…For environment perception and localization, the detection of landmarks has to be performed in real-time. According to previous research (Albrecht et al, 2019) algorithms should run with at least 20 Hz. This image was generated in under 30 ms making it usable for real-time application in an autonomous vehicle, even though further processing has to be performed to transform these ROIs into line landmarks.…”

“…Automated vehicles are not able to cover all possible driving situations only by using camera data, so a fusion with ranging sensors like laser scanners and radars are needed. Our previous concept (Albrecht et al, 2019) focused on the sensor data fusion of laser scanner point clouds with segmented road images from horizontal cameras in an low-level fusion approach. In this extension, we include objects detected by the top-view camera system in a late fusion approach.…”