We are developing an experimental testbed to explore hybrid vehicular-to-everything (V2X)communication and computing systems. Two experimental vehicles are currently instrumented with multiple sensors and hybrid wireless communication technologies including sub-6 GHz and mmWave radios mounted on the top rack or inside of the car. Each vehicle contains Onboard Units (OBUs), to support sensor data acquisition and local computing. Multiple Road-Side Units (RSUs), with overlapping coverage, consisting of sub-6 GHz and mmWave radios along with edge-computing nodes, and street IoTs are being deployed as well. The testbed enables real-world data collection for training AI models along with evaluation of the performance of the developed algorithms using the real world latency, computation, and bandwidth needs of multiple vehicles and roadway users.
Sensing and Computing Capabilities
We have developed a preliminary testbed over the last year consisting of two prototype vehicles equipped with multiple cameras, radars, and GPS. We use the power efficient NVIDIA Jetson boards with inbuilt GPUs to prototype the computing capabilities of OBUs and RSU nodes. RSU nodes are equipped with a varying number of Jetson boards in order to evaluate the impact of various levels of computing capabilities on our proposed data fusion and analytics algorithms. The vehicle’s cameras are capable of both RGB and Depth sensing, with the interior camera also being capable of Near Infrared (NIR) imaging and multiple exterior facing cameras arranged to support stereo imaging. The radars deployed on the vehicles are TI 1-degree radars which can be synchronized with one another, as well as with the cameras, in order to support homogeneous and heterogeneous sensor fusion.
We are currently in the process of outfitting a third vehicle that will also include IMU and lidar sensors as well as access to the CAN bus that allows the collection of a more detailed status of the host vehicle. Similarly, we also plan to deploy various street IoTs such as cameras and lidars throughout the UCSD campus as part of the testbed.
Hybrid Communications with C-V2X and mmWave
In the preliminary version of the testbed, the prototype vehicles connected to RSUs mounted on the rooftops of Jacobs Hall and Atkinson Hall, with the small cells providing overlapping coverage to Voigt Drive and other cross streets below. Each vehicle communicated using USRP B210 radios while the RSUs utilized USRP N310s and ran the open-source srsLTE protocol stack. We are currently migrating the sub-6 GHz communication technology from these Software Defined Radios, which are unreliable, to a commercial C-V2X capability that will provide more robust communications with our vehicles at extended ranges.
While sub-6 GHz C-V2X technologies will provide more robust communications, the achievable data rates are insufficient for full data sharing amongst vehicles and infrastructure. We have developed two mmWave radios for experimentation with mmWave V2X that could enable multi-gigabits per second communication rates between the RSUs and vehicles. The two radio types are briefly described below, but are more extensively documented at m3.ucsd.edu.
Type A: Partially programmable 802.11ad-compatible mmWave radio with 36-element or 288-element phased-array, able to reconfigure the codebook entries, electronically steer the beam direction, and measure the per-beam CSI in real-time. We have deployed 8 of such radios as base stations on the UCSD campus, to form a programmable mmWave network with integrated access and backhaul capabilities. Type B: Fully programmable massive MIMO mmWave software-radio, composed of an array of phased-arrays. Each mmWave MIMO software-radio will have (i) 4 RF front-ends supporting 60 GHz (57-64 GHz) bands. (iii) 4 programmable phased-arrays attached to the RF front-ends, each with 36 (6 × 6) or 32 antenna elements. This platform can reuse existing software-radios like USRP and WARP as baseband processing units.
Type B: Fully programmable massive MIMO mmWave software-radio, composed of an array of phased-arrays. Each mmWave MIMO software-radio will have (i) 4 RF front-ends supporting 60 GHz (57-64 GHz) bands. (iii) 4 programmable phased-arrays attached to the RF front-ends, each with 36 (6 × 6) or 32 antenna elements. This platform can reuse existing software-radios like USRP and WARP as baseband processing units.
Testbed Deployment in Cooperation with City Partners
The testbed is currently deployed on UCSD’s campus, but we are further developing and expanding the testbed to the city of Carlsbad. The extension to Carlsbad will focus on the use case of a next generation smart intersection, including deployment of lidar and camera systems at a selected intersection, connected with a RSU equipped with both sub-6 GHZ as well as our mmWave radios. The Carlsbad deployment will allow us to collect real-time data on pedestrians and vehicles approaching the intersection, develop AI-based models to predict intent of pedestrians and vehicles to enter the intersection, and demonstrate the usefulness of the collaborative perception algorithms to send timely preventative warnings to pedestrians and vehicles to avoid potential collisions. The prototype deployment will also allow us to test, validate and demonstrate in real-world environments our proposed mmWave and MMIMO techniques in being able to satisfy the ultra-high bandwidth and ultra-low latency requirements of the smart intersection use case. We are also in conversation with SANDAG who has taken interest in the project, as well as our partner cities City of Chula Vista and San Diego, and hope to expand our prototyping and deployment opportunities elsewhere.