We present a novel head-mounted display setup that uses the pinhole imaging principle coupled with a low-latency dynamic pupil follower. A transmissive LCD is illuminated by a single LED backlight. LED illumination is focused onto the viewer's pupil to form an eyebox smaller than the average human pupil, thereby creating a pinhole display effect where objects at all distances appear in focus. Since nearly all the light is directed to the viewer's pupil, a single low-power LED for each primary color with 0.42 lumens total output is sufficient to create a bright and full-color display of 360 cd/m 2 luminance. In order to follow the viewer's pupil, the eyebox needs to be steerable. We achieved a dynamic eyebox using an array of LEDs that is coupled with a real-time pupil tracker. The entire system is operated at 11 msec motion-to-photon latency, which meets the demanding requirements of the real-time pupil follower system. Experimental results effectively demonstrated our headmounted pinhole display with 37° FOV and very high light efficiency, equipped with a pupil follower with low motion-to-photon latency.

Machine learning (ML) has already been adopted in vehicular networks for such applications as autonomous driving, road safety prediction and vehicular object detection, due to its model-free characteristic, allowing adaptive fast response. However, the training of the ML model brings significant complexity for the data transmission between the learning model in a cloud server and the edge devices in the vehicles. Federated learning (FL) framework has been recently introduced as an efficient tool with the goal of reducing this transmission overhead while also achieving privacy through the transmission of only the gradients of the learnable parameters rather than the whole dataset. In this article, we provide a comprehensive analysis of the usage of FL over ML in vehicular network applications to develop intelligent transportation systems. Based on the real image and lidar data collected from the vehicles, we illustrate the superior performance of FL over ML in terms of data transmission complexity for vehicular object detection application. Finally, we highlight major research issues and identify future research directions on system heterogeneity, data heterogeneity, efficient model training and reducing transmission complexity in FL based vehicular networks.

No abstract

Autonomous vehicles need to estimate the relative poses, i.e., position and orientation, of the surrounding vehicles on the road with at least 50 Hz rate and cm-level accuracy for platooning and collision avoidance applications. The LIDAR/camera solutions currently used for vehicle pose estimation do not satisfy these rate and accuracy requirements, necessitating complementary technologies. Vehicular visible light positioning (VLP) is a highly suitable complementary technology due to its high rate and high accuracy, exploiting the line-of-sight propagation feature of the visible light communication (VLC) signals from LED head/tail lights. However, existing vehicular VLP solutions impose restrictive requirements, e.g., high-bandwidth circuit, base station and VLC waveform constraints, and work for limited relative vehicle orientations, thus, cannot be extended for pose estimation. This paper proposes a VLP-based vehicle pose estimation (VLP-VPE) solution that eliminates these restrictive requirements by a novel VLC receiver design and a novel pose estimation algorithm. The VLC receiver, named QRX, is low-cost/size, and enables high-rate VLC and high-accuracy angle-of-arrival sensing, simultaneously, via the usage of a quadrant photodiode. The estimation algorithm first uses two of the designed QRXs to determine the positions of two head/tail light VLC transmitters on a neighbouring vehicle via triangulation, and then determines the 2D pose of the vehicle based on these two positions. Sensitivity analyses and simulations using traffic data from the Simulation of Urban Mobility (SUMO) demonstrate that the proposed solution performs pose estimation at cm-level accuracy and kHz rate under realistic road and channel conditions, demonstrating its eligibility for platooning and collision avoidance applications.