Consistent decentralized cooperative localization for autonomous vehicles using LiDAR, GNSS, and HD maps

Abstract

To navigate autonomously, a vehicle must be able to localize itself with respect to its driving environment and the vehicles with which it interacts. This work presents a decentralized cooperative localization method. It is based on the exchange of Local Dynamic Maps (LDM), which are cyberphysical representations of the physical driving environment containing poses and kinematic information about nearby vehicles. An LDM acts as an abstraction layer that makes the cooperation framework sensor-agnostic, and it can even improve the localization of a sensorless communicating vehicle. With this goal in mind, this work focuses on the property of consistency in LDM estimates. Uncertainty in the estimates needs to be properly modeled, so that the estimation error can be statistically bounded for a given confidence level. To obtain a consistent system, we first introduce a decentralized fusion framework that can cope with LDMs whose errors have an unknown degree of correlation. Second, we present a consistent method for estimating the relative pose between vehicles, using a 2D LiDAR with a point-to-line metric within an iterative-closest-point approach, combined with communicated polygonal shape models. Finally, we add a bias estimator in order to reduce position errors when non-differential GNSS receivers are used, based on visual observations of features geo-referenced in a High-Definition (HD) map. Real experiments were conducted, and the consistency of our approach was demonstrated on a platooning scenario using two experimental vehicles. The full experimental dataset used in this work is publicly available. A Poses transformations operatorsAs we use only direct orthonormal frames, the definition of one frame in its reference frame is equivalent to the frame transformation between these two frames and to the pose of this frame in its reference frame. The position corresponds to the origin and the orientation to the one of the x axes of the frame.

Degradation state detection and local map optimization for enhancing the SOTIF of map-matching-based fusion localization system

“…Zhang et al [19] proposed a direct vector map-based positioning system within a graph optimization framework. Additionally, Héry et al [20] introduced a distributed cooperative localization method based on the exchange of local dynamic maps containing neighboring vehicles' pose and motion information. While the aforementioned studies achieve high localization accuracy and robustness in common scenarios, they often overlook potential issues in SOTIF scenarios.…”

Localization for self-driving vehicles based on deep learning networks and RGB cameras

“…The method assumed preprocessed and calibrated LiDAR data, which may not be accurate in real life [22]. Héry et al (2021) LiDAR, global navigation satellite system (GNSS), and HD maps enabling AV decentralized cooperative localization. The proposed solution provided reliable localization information to autonomous cars in GNSS-deficient environments.…”

“…Unfortunately, the system required AV to interact and share sensor measurements. Communication bandwidth may limit applications [23]. Qin et al (2021) provided autonomous driving visual localization road map.…”

Data Fusion with Split Covariance Intersection for Cooperative Perception

“…The Covariance Intersection Filter (CIF) [13] which is usually given in informational form is here given in a Kalman form for the sake of consistency, according to [2].…”

“…The main issue with this family of approaches is its pessimism [1]. To alleviate this issue, approaches such as in [2] have been implemented, where local data is carefully separated from shared data in order to apply a Kalman Filter (KF) on the local data and CI to the shared one. This showed good performance, especially in terms of consistency of the estimates.…”