Simultaneous Localization and Map Change Update for the High Definition Map-Based Autonomous Driving Car

Abstract

High Definition (HD) maps are becoming key elements of the autonomous driving because they can provide information about the surrounding environment of the autonomous car without being affected by the real-time perception limit. To provide the most recent environmental information to the autonomous driving system, the HD map must maintain up-to-date data by updating changes in the real world. This paper presents a simultaneous localization and map change update (SLAMCU) algorithm to detect and update the HD map changes. A Dempster–Shafer evidence theory is applied to infer the HD map changes based on the evaluation of the HD map feature existence. A Rao–Blackwellized particle filter (RBPF) approach is used to concurrently estimate the vehicle position and update the new map state. The detected and updated map changes by the SLAMCU are reported to the HD map database in order to reflect the changes to the HD map and share the changing information with the other autonomous cars. The SLAMCU was evaluated through experiments using the HD map of traffic signs in the real traffic conditions.

MMW Radar-Based Technologies in Autonomous Driving: A Review

“…Technologies used in this process include the sensor perception algorithm, environmental map construction, and self-vehicle pose estimation. Meanwhile, as the driving environment changes with time, environment mapping also needs the support of map updating technology [ 81 ].…”

Updating Point Cloud Layer of High Definition (HD) Map Based on Crowd-Sourcing of Multiple Vehicles Installed LiDAR

“…Kim et al [31], [32] researched adding of new feature maps in the HD map based on crowd-sourced measurements; as a result, streetlights and traffic signs were added into the HD map as new features. Jo et al [33] managed the traffic signs in the HD map by surveying whether traffic signs in the HD map were deleted or the new traffic signs were added based on the evidential approach. Pannen et al [34] kept lane markings in the HD map up-to-date using the three pipelines (change detection, job creator, and map update).…”

High Definition 3D Map Creation Using GNSS/IMU/LiDAR Sensor Integration to Support Autonomous Vehicle Navigation

“…Vehicle-to-roadside-infrastructure (V2I) and vehicle-to-vehicle (V2V) communications help to improve traffic safety and autonomous driving functionality [4]. It is expected that fully automated cars will be commercialized, and will appear on the roads in the coming years [5], will prevent driver-related accidents [6], and will decrease transportation problems such as regulating traffic flow [4]. Perception, localization and mapping, path planning, decision making, and vehicle control are the main components of AV technology [7].…”

“…These techniques require more computationally intensive algorithms and may be subject to more uncertainty depending on the sensors used and on the surroundings [7]. Due to the limitations of the sensors, such as perception range and recognition performance, AVs cannot detect distant objects or objects blocked by obstacles in real time [6]. Using HD maps overcomes these limitations and offers a detailed representation of the surroundings of the AV, and thus, the perception task of AV systems is significantly assisted; it is much easier to find and identify objects if they are known.…”