In recent years, cooperative positioning technologies have emerged as promising augmentation systems for providing high-accuracy positioning (HAP) in cooperative intelligent transportation systems (C-ITS). Among the approaches, implicit cooperative positioning (ICP) takes advantage of shared target detections between vehicles to create common reference points for localization refinement. Their performance, however, is limited by reliance on predefined parametric models, low scalability and communication overhead. To address these problems, this paper introduces a deep multi-agent reinforcement learning (MARL) framework modelled as a decentralized-partially observable Markov decision process (Dec-POMDP). We propose an ICP-multi-agent proximal policy optimization (MAPPO) algorithm, where distributed agents (i.e., the connected vehicles) learn their dynamics and those of the surrounding targets by performing belief estimation over dynamic cooperation graphs that are continuously adjusted by de/activating communication links with neighbors agents. A C-ITS scenario is simulated in a CARLA environment accounting for realistic vehicle dynamics and inter-vehicle communications. The findings reveal that our ICPMAPPO algorithm, leveraging dynamic decentralized execution and centralized training, outperforms ICP in terms of positioning accuracy and communication efficiency.

In the rapidly evolving domain of forthcoming 6th generation (6G) networks, achieving precise dynamic positioning down to the centimeter becomes critical, particularly in complex urban scenarios as those envisioned for cooperative intelligent transport systems (C-ITSs). To face the challenges introduced by severe path loss and blockages in new 6G frequency bands, machine learning (ML) provides innovative strategies to extract locational intelligence from wide-band space-time radio signals. This paper proposes the integration of Bayesian neural networks (BNNs) into cellular multi-base station (BS) tracking systems, where uncertainties of BNNs account for finite training sets and measurement errors. Our approach utilizes a deep learning (DL)-based autoencoder (AE) structure that exploits the full channel impulse response (CIR) to infer location-centric attributes in both line-of-sight (LoS) and non-LoS (NLoS) conditions. Validations in a 3rd Generation Partnership Project (3GPP) compliant urban micro (UMi) setting, simulated with ray-tracing and traffic simulations, demonstrate the superior performances of BNN-based tracking with respect to both traditional geometric-based tracking methods and state-of-the-art DL models.

In the evolving landscape of 5G new radio and related 6G evolution, achieving centimeter-level dynamic positioning is pivotal, especially in cooperative intelligent transportation system frameworks. With the challenges posed by higher path loss and blockages in the new frequency bands (i.e., millimeter waves), machine learning (ML) offers new approaches to draw location information from space-time wide-bandwidth radio signals and enable enhanced location-based services. This paper presents an approach to real-time 6G location tracking in urban settings with frequent signal blockages. We introduce a novel teacher-student Bayesian neural network (BNN) method, called Bayesian bright knowledge (BBK), that predicts both the location estimate and the associated uncertainty in real-time. Moreover, we propose a seamless integration of BNNs into a cellular multi-base station tracking system, where more complex channel measurements are taken into account. Our method employs a deep learning (DL)-based autoencoder structure that leverages the complete channel impulse response to deduce location-specific attributes in both line-of-sight and non-line-of-sight environments. Testing in 3GPP specification-compliant urban micro (UMi) scenario with ray-tracing and traffic simulations confirms the BBK’s superiority in estimating uncertainties and handling out-of-distribution testing positions. In dynamic conditions, our BNN-based tracking system surpasses geometric-based tracking techniques and state-of-the-art DL models, localizing a moving target with a median error of 46 cm.

This paper considers the problem of cooperative localization of passive objects in a vehicular environment through the fusion of lidar point clouds collected at different moving vehicles and sent to the road infrastructure. Object localization is then used to improve the position estimate of vehicles according to the implicit cooperative positioning paradigm. At first, each vehicle uses a deep neural network (a 3D object detector) to process its lidar point cloud and localize static objects. Then, the set of estimated bounding boxes is sent to the road infrastructure, which performs data association through a message passing neural network to identify the set of measurements originating from the same detected object. Lastly, cooperative localization of objects is backward used to improve vehicle positioning. Simulations of a realistic cooperative lidar sensing scenario with CARLA software highlight improved positioning compared to non-cooperative tracking.

In application verticals that rely on mission-critical control, such as cooperative intelligent transport systems (C-ITS), 5G-Advanced networks must be able to provide dynamic positioning with accuracy down to the centimeter level. To achieve this level of precision, technology enablers, such as massive multiple-input multiple-output (mMIMO), millimeter waves (mmWave), machine learning and cooperation are of paramount importance. In this paper, we propose a cooperative deep learning (DL)-based positioning methodology that combines these key technologies into a new promising solution for precise 5G positioning. Sparse channel impulse response (CIR) data are used by the positioning infrastructure to extract position-dependent features. We model the problem as a joint task composed of non-line-of-sight (NLOS) identification and position estimation which permits to suitably handle geometrical location measurements and channel fingerprints. The network of base stations (BSs) automatically steers between egocentric (in case of NLOS) and cooperative (for LOS) positioning mode. We perform extensive standard-compliant simulations in a 5G urban micro (UMi) vehicular scenario obtained by ray-tracing and simulation of urban mobility (SUMO) software. Results show that the proposed cooperative DL architecture is able to outperform conventional geometrical positioning algorithms operating in LOS by 47%, achieving a median error of 71 cm on unseen trajectories.

In mission-critical verticals such as automated driving, 5G-advanced networks must provide centimeter-level dynamic positioning along with ultra-reliable low-latency communication services. Massive Multiple-Input Multiple-Output (mMIMO) and millimeter waves (mmWave) are the key enablers, allowing high accuracy angle and delay estimation. Still, extracting such information from highly-dimensional Channel Impulse Responses (CIRs) results in a complex task, due to channel sparsity and intermittent blockage. In this paper we focus on non-line-of-sight (NLOS) identification from CIR data, proposing a Deep Autoencoding Kernel Density Model (DAKDM) to characterize the statistics of the channel latent features. We formulate the problem as a semi-supervised anomaly detection task in which only LOS samples, i.e., normal data, are adopted for training. DAKDM is a single-stage training model that takes as input the full CIR thanks to an AutoEncoder (AE) structure. The proposed method is able to learn the latent distribution by means of a Kernel Density Estimator (KDE) in combination with a deep learning likelihood network. We validate the proposed solution in a 5G Urban micro (UMi) vehicular scenario. Results show that the proposed model can significantly outperform conventional algorithms and obtain similar performances to variational Bayes algorithms at one tenth of the inference time.