PROJECT OVERVIEW

We envision the need for a novel and completely collaborative approach for safer, more efficient and eco-friendly commutes in addition to current day V2V propositions. Real-time streaming data from multiple participants - vehicles, pedestrians and smart street IoTs (like smart traffic lights and pedestrian crossings) - when aggregated, fused and analyzed can provide an accurate, complete and dynamic street situational awareness to all the street participants, leading to collaborative and personalized guidance and advanced warnings services. As part of the ‘Enabling Collaborative Awareness for Assisted and Autonomous Driving’ project, we are creating a collaborative data fusion and machine vision/learning platform as well as a novel computing and communication architecture and testbed to support the collaborative platform.

READ FULL OVERVIEW
object detection

Connected and Autonomous Vehicles

Collaborative Vehicular Vision

Principal Investigator
Sujit Dey, Truong Nguyen
Research Students
Sam Thornton, Ji Dai

This project focuses on improving the accuracy of object recognition and situational awareness of connected and autonomous vehicles by having multiple vehicles and smart street IoTs (like smart lights and smart intersections) combine their sensor data through a mobile edge computing (MEC) node located at a nearby roadside unit (RSU). A vehicle, even one with the most sophisticated array of sensors, can only perceive a limited area around itself; this vision is further impacted by possible adverse weather and light conditions and occlusions created by the presence of other road users, like other vehicles and pedestrians, as well as buildings and road infrastructure.

READ MORE

Autonomous Driving Sensors

Connected and Autonomous Vehicles

Cooperative Driving with Highly Improved Mapping & Localization, Perception, and Path Planning

Principal Investigator
Dinesh Bharadia, Tara Javidi
Research Students
Yongxi Lu, Aman Raj, Samuel Sunarjo, Ish Jain, Yeswanth Reddy, Yue Meng

Autonomous and automated driving requires sensing of the environment based on which actions related to driving are performed. V2V wireless communications can significantly improve the vehicles’ sensing ability and solve many of these challenges (non-line of sight, long range or bad weather sensing) by combining of sensing and driving information collected from multiple cars (cooperative data). In summary, this project aims at characterizing the cooperative sensing gain via optimized information acquisition strategies enabled by wireless links between vehicles.

READ MORE

Mimo photo

Connected and Autonomous Vehicles

Channel Modeling and Transceiver Architectures in Support of High Data Rate Communications in Mobile Environments

Principal Investigator
Bhaskar D. Rao
Research Students
Aditya Sant, Rohan Pote

The project will examine massive MIMO communication to support the high data rate needs of autonomous driving. Both sub 6 Ghz and mm-Wave communication will be of interest with some preference to mm-Wave communication. The specific aims of our project are: 1) Development and analysis of low complexity receiver and transmitter architectures (mm-Wave) in support of the communication needs. In particular, development of suitable antenna array architectures along with the RF chains topology for rich channel sensing. 2) Novel channel sensing methods that are synergistic with the architectures and development of channel estimation techniques that enable a richer characterization of the communication environment than hitherto possible. 3) Novel channel models to incorporate mobility as well as the development of algorithms to track the channel in mobile environments.

READ MORE

V2X image

Connected and Autonomous Vehicles

CWC 5G V2X Testbed

Principal Investigator
Xinyu Zhang
Research Students
Renjie Zhang

The CWC research team is developing an experimental testbed to explore 4G/5G vehicular-to-everything (V2X) communication and network systems.  The testbed consists of 3 small-cell base stations, deployed on rooftops on campus and connected to a core-network server. Two experimental vehicles are instrumented and equipped with 4G/5G radios, mounted on the top rack or inside. Each base station and mobile device comprises of two software radios, running at sub-6GHz and millimeter-wave frequencies, respectively. These software radios are programmable from physical layer signal processing all the way up to mobile application layer, thus enabling full-stack experimental research in 4G and 5G.

READ MORE