Collaborating Authors


Turning Traffic Monitoring Cameras into Intelligent Sensors for Traffic Density Estimation Artificial Intelligence

Accurate traffic state information plays a pivotal role in the Intelligent Transportation Systems (ITS), and it is an essential input to various smart mobility applications such as signal coordination and traffic flow prediction. The current practice to obtain the traffic state information is through specialized sensors such as loop detectors and speed cameras. In most metropolitan areas, traffic monitoring cameras have been installed to monitor the traffic conditions on arterial roads and expressways, and the collected videos or images are mainly used for visual inspection by traffic engineers. Unfortunately, the data collected from traffic monitoring cameras are affected by the 4L characteristics: Low frame rate, Low resolution, Lack of annotated data, and Located in complex road environments. Therefore, despite the great potentials of the traffic monitoring cameras, the 4L characteristics hinder them from providing useful traffic state information (e.g., speed, flow, density). This paper focuses on the traffic density estimation problem as it is widely applicable to various traffic surveillance systems. To the best of our knowledge, there is a lack of the holistic framework for addressing the 4L characteristics and extracting the traffic density information from traffic monitoring camera data. In view of this, this paper proposes a framework for estimating traffic density using uncalibrated traffic monitoring cameras with 4L characteristics. The proposed framework consists of two major components: camera calibration and vehicle detection. The camera calibration method estimates the actual length between pixels in the images and videos, and the vehicle counts are extracted from the deep-learning-based vehicle detection method. Combining the two components, high-granular traffic density can be estimated. To validate the proposed framework, two case studies were conducted in Hong Kong and Sacramento. The results show that the Mean Absolute Error (MAE) in camera calibration is less than 0.2 meters out of 6 meters, and the accuracy of vehicle detection under various conditions is approximately 90%. Overall, the MAE for the estimated density is 9.04 veh/km/lane in Hong Kong and 1.30 veh/km/lane in Sacramento. The research outcomes can be used to calibrate the speed-density fundamental diagrams, and the proposed framework can provide accurate and real-time traffic information without installing additional sensors.

Elon Musk wins approval to build a 29-mile tunnel system underneath the Las Vegas strip

Daily Mail - Science & tech

Billionaire entrepreneur Elon Musk has won approval to build a 29-mile tunnel system underneath the Las Vegas strip. It will allow up to 57,000 passengers to hitch rides in Teslas to and from casinos every hour, as well as to the city's airport and the Raiders football stadium. The SpaceX founder's Boring Company already operates a smaller version of the'Vegas Loop' system underneath the Las Vegas Convention Center, which opened earlier this year to lackluster reviews. Instead of futuristic cars zipping people from place to place at high speeds, it features regular Tesla vehicles being driven by humans trundling through a tunnel at just 35mph. However, a huge city-wide expansion of the tunnels, which was proposed by The Boring Company in December last year, has now been approved by Vegas officials.

Smart Automotive Technology Adherence to the Law: (De)Constructing Road Rules for Autonomous System Development, Verification and Safety Artificial Intelligence

Driving is an intuitive task that requires skills, constant alertness and vigilance for unexpected events. The driving task also requires long concentration spans focusing on the entire task for prolonged periods, and sophisticated negotiation skills with other road users, including wild animals. These requirements are particularly important when approaching intersections, overtaking, giving way, merging, turning and while adhering to the vast body of road rules. Modern motor vehicles now include an array of smart assistive and autonomous driving systems capable of subsuming some, most, or in limited cases, all of the driving task. The UK Department of Transport's response to the Safe Use of Automated Lane Keeping System consultation proposes that these systems are tested for compliance with relevant traffic rules. Building these smart automotive systems requires software developers with highly technical software engineering skills, and now a lawyer's in-depth knowledge of traffic legislation as well. These skills are required to ensure the systems are able to safely perform their tasks while being observant of the law. This paper presents an approach for deconstructing the complicated legalese of traffic law and representing its requirements and flow. The approach (de)constructs road rules in legal terminology and specifies them in structured English logic that is expressed as Boolean logic for automation and Lawmaps for visualisation. We demonstrate an example using these tools leading to the construction and validation of a Bayesian Network model. We strongly believe these tools to be approachable by programmers and the general public, and capable of use in developing Artificial Intelligence to underpin motor vehicle smart systems, and in validation to ensure these systems are considerate of the law when making decisions.

2024 will be the year Apple and Amazon releases us from our automotive prison


As a product of Gen X, I am perhaps among the last generation to be obsessed with the notion of car ownership. I love the different body designs. I love how each one drives differently. I love the history and culture that surrounds the different automotive brands. I love the activity of going out for rides with no objective other than to take the top down on my Camaro convertible and drive.

Building Trust in Autonomous Vehicles: Role of Virtual Reality Driving Simulators in HMI Design Artificial Intelligence

The investigation of factors contributing at making humans trust Autonomous Vehicles (AVs) will play a fundamental role in the adoption of such technology. The user's ability to form a mental model of the AV, which is crucial to establish trust, depends on effective user-vehicle communication; thus, the importance of Human-Machine Interaction (HMI) is poised to increase. In this work, we propose a methodology to validate the user experience in AVs based on continuous, objective information gathered from physiological signals, while the user is immersed in a Virtual Reality-based driving simulation. We applied this methodology to the design of a head-up display interface delivering visual cues about the vehicle' sensory and planning systems. Through this approach, we obtained qualitative and quantitative evidence that a complete picture of the vehicle's surrounding, despite the higher cognitive load, is conducive to a less stressful experience. Moreover, after having been exposed to a more informative interface, users involved in the study were also more willing to test a real AV. The proposed methodology could be extended by adjusting the simulation environment, the HMI and/or the vehicle's Artificial Intelligence modules to dig into other aspects of the user experience.

Tesla may build 12-seat electric VANS that zip passengers at 127 mph through an underground tunnel

Daily Mail - Science & tech

Tesla is developing its own electric van for zipping passengers through its underground'boring' tunnels. According to a report from The Mercury News, San Bernardino County Transportation Authority will work with Tesla - and its sister drilling company Boring Company - to develop a 12-seat electric van for transporting passengers through a nearly 3-mile tunnel. The vans will be used in a recently approved connector line between Rancho Cucamonga and the Ontario International Airport. Tesla may develop an electric van capable of caring passengers between a 3-mile underground tunnel connecting Rancho Cucamonga and the Ontario International Airport. in San Bernardino County. While plans originally called for specially designed cars, the $60 million project will use the vans instead to eventually carry 1,200 passengers per day or about 10 million per year according to The Mercury News.

Hertz teams up with biometric firm Clear to let travelers rent a car by scanning their face

Daily Mail - Science & tech

Biometric screening is expanding to the rental car industry. Hertz said Tuesday it is teaming up with Clear, the maker of biometric screening kiosks found at many airports, in an effort to slash the time it takes to pick up a rental car. Clear hopes it will lead more travelers to its platform, which has 3 million members in the U.S. It's the latest place consumers will find biometric technology, which has migrated over the last 50 years from secure government facilities and banks to airports, stadiums and even smartphones that unlock with the touch a fingerprint. Hertz is the first rental car company to use the technology. In a first for the rental car industry, Hertz is teaming up with Clear, the maker of biometric screening kiosks found at many airports and stadiums.

Cadillac Super Cruise hands-free driving software takes on Tesla Autopilot

Los Angeles Times

A reporter jots a quick note as Super Cruise handles the steering on Interstate 280 near Palo Alto. The light bar on the wheel glows green to signal that everything's cool. A reporter jots a quick note as Super Cruise handles the steering on Interstate 280 near Palo Alto. The light bar on the wheel glows green to signal that everything's cool. Tesla Autopilot is about to encounter some serious competition.

Juno Takes on Uber

The New Yorker

The LaGuardia Plaza Hotel is a four-minute drive from LaGuardia Airport, in Queens, and on a recent August afternoon nearly every car parked in the hotel's lot was black. One after the other, men in shirtsleeves pulled up in Chevy Suburbans and GMC Yukon XLs and gleaming Lexus RS 300s with leather-trimmed seats, got out, then made their way across the marble lobby and up a flight of stairs. A brightly smiling woman approached them as they congregated around a registration desk. She jotted the letters onto a yellow sticky note and worked her way down the line. "Do you have an appointment? The men were black-car drivers, currently working for the ride-summoning companies Uber or Lyft, or both, and they were there, in all likelihood, because another driver had told them that they could get more money, and better treatment, if they signed up to drive for a new rival, Juno. New York City--which has no shortage of ways to get around, from pedicabs to one of the largest public-transportation systems in the world--is just one stage upon which a handful of companies are fighting to dominate the future of personal transportation. Juno has decided that the most effective way to do that is by being extra-nice to the drivers. After the men registered, they were ushered into a waiting room, where draped café tables had been set up with brochures: "How to Be a 5 Star Juno Driver." The drivers were soon called by name--"Khaleed?" "Julio?"--and brought into another room, where a Juno manager, Lucas Smith, was waiting for them with a laptop and an overhead projector.

Welcome to the Metastructure: The New Internet of Transportation


Though I haven't lived there for nearly three decades, I still consider myself a citizen of Los Angeles. That means, among other things, I drive. For me, a car is like a suit or a good exoskeleton. Road trips, going 100 miles per hour on a freeway, racing through Park La Brea--they're all sewn as tightly into my DNA as ice-skating in Central Park is for a New Yorker. Despite that heritage, I've been running an experiment on myself and my hometown. My last three trips there, I didn't rent a car; it's been nothing but taxis, Uber, and one time I borrowed my dad's. Not only did I move through space and time every bit as efficiently--more, if you believe that screwing around on Twitter and email is useful--I took new routes.