AI-powered cruise control system may pave the way to fuel efficiency and traffic relief

Mar 9, 2023

3 min

Dan Work


The CIRCLES Consortium, consisting of Vanderbilt University, UC Berkeley, Temple University and Rutgers University-Camden, in coordination with Nissan North America and the Tennessee Department of Transportation, concluded a five-day open-track experiment on Nov. 18.


Congestion Impacts Reduction via CAV-in-the-loop Lagrangian Energy Smoothing (CIRCLES)


Researchers tested an AI-powered cruise control system designed to increase fuel savings and ease traffic using 100 specially equipped Nissan Rogue vehicles.


The experiment—which ran from Nov. 14 through Nov. 18 on a sensor-filled portion of Interstate 24—is based on the results from an earlier, closed-track study where a single smart vehicle smoothed human-caused traffic congestion, leading to significant fuel savings.


A single AI-equipped vehicle could influence the speed and driving behavior of up to 20 surrounding cars, causing a kind of positive ripple effect in day-to-day traffic. The CIRCLES Consortium will spend the next several months analyzing data collected on the AI-equipped vehicles and their impact on the flow of traffic over the duration of the experiment.


The test was conducted on the recently opened I-24 MOTION testbed, the only real-world automotive testing environment of its kind in the world. Stretching for four miles just southeast of downtown Nashville, the smart highway is equipped with 300 4K digital sensors capable of logging 260,000,000 vehicle-miles of data per year.


The CIRCLES Consortium research is supported by the National Science Foundation and the U.S. Departments of Transportation and Energy. Support was also provided by Toyota North America and General Motors. The experiment included Toyota RAV4 and Cadillac XT5 vehicles.



Preliminary vehicle and traffic flow detection in the I-24 Mobility Technology Interstate Observation Network (MOTION).


“On November 16 alone, the system recorded a total of 143,010 miles driven and 3,780 hours of driving. The I-24 MOTION system, combined with vehicle energy models developed in the CIRCLES project, provided an estimation of the fuel consumption of the whole traffic flow during those hours. The concept we are hoping to demonstrate is that by leveraging this new traffic system to collect data and estimate traffic and applying artificial intelligence technology to existing cruise control systems, we can ease traffic jams and improve fuel economy,” the CIRCLES team said in a joint statement.


“Nissan has always been a pioneer in automotive innovation, and with our long-term vision, Nissan Ambition 2030, we know our future is autonomous, connected and electric,” said Liam Pedersen, deputy general manager at the Nissan Alliance Innovation Lab in California’s Silicon Valley. “CIRCLES shares our common goal of building a safer, cleaner world by empowering mobility.”


“When it comes to transportation and mobility in Tennessee, we are at a critical juncture,” said Deputy Governor and TDOT Commissioner Butch Eley. “Traffic congestion is now becoming more prominent throughout Tennessee, and not just in urban areas. Addressing these challenges will force us to think critically about solutions, as transportation infrastructure projects traditionally are not identified nor completed before traffic congestion more dramatically affects our quality of life. One of these solutions is greater use of technology to enhance mobility. We are confident that this project and others like it will further strengthen Tennessee’s reputation for being a hub of automotive excellence.”



“The I-24 MOTION project is a first-of-its-kind testbed, where we’ll be able to study in real time the impact connected and autonomous vehicles have on traffic in an open road setting,” said Meredith Cebelak, adjunct instructor in civil and environmental engineering at Vanderbilt and Tennessee transportation and transportation systems management and operations department leader at Gresham Smith. “The permanent infrastructure has been designed and installed, meaning the testbed will always be ‘on’ and available to researchers. By unlocking a new understanding of how these vehicles influence traffic, vehicle, infrastructure, and traffic management strategies, design can be optimized to reduce traffic concerns in the future to improve safety, air quality and fuel efficiency.” 


“Partnership across universities, government and the private sector is the key to pioneering projects like this one,” Vice Provost for Research and Innovation Padma Raghavan said. “From its earliest inception, all the partners in this effort have played vital roles. That trusted collaboration continues as the team analyzes results to seek new insights to address pressing challenges in transportation in Tennessee and beyond.”
Connect with:
Dan Work

Dan Work

Professor of Civil and Environmental Engineering

Expert in self-driving cars and traffic management.

Adaptive Cruise ControlTrafficInverse ModelingConnected and Autonomous VehiclesTraffic Estimation and Control

You might also like...

Check out some other posts from Vanderbilt University

2 min

Vanderbilt debate director and rhetoric expert on Harris-Trump debate expectations and tips

John Koch, senior lecturer and director of debate at Vanderbilt University, is available for commentary on the Harris-Trump presidential debate. A recognized scholar on presidential communication and rhetoric, John uses a wide range of methods to understand and explain political and policy debates. His research is guided by the question of how we can improve citizenship practices and debates within our political culture. His most recent co-authored scholarly article explored the history of presidential debates and how we can improve them. He has served as chair of the National Communication Association’s Argumentation and Forensics Division and the Committee on International Discussion and Debate. His research has appeared in Contemporary Argumentation and Debate, the National Forensic Journal, Studies in Debate and Oratory and various book chapters on presidential rhetoric. Currently, he serves as the Director of Debate of Vanderbilt’s internationally renowned and award-winning debate program. Topics he can speak to include: What arguments to expect from the candidates What each candidate needs to do and not do in the debate How to determine who wins a debate What to watch for/what issues might come up in the debate History of presidential debates The usefulness of presidential debates and how we might improve them How adults can discuss politics and debates with their children by watching debates together After debate analysis of who may have won and what issues/moments may be salient to voters The debate styles of the candidates and their histories in debates Differences in debate style we can expect between Trump and Harris Differences in how Trump may approach the debate with Harris vs. how he approached Biden

5 min

While Marijuana Will Soon be Rescheduled, the Federal Government’s Drug Scheduling System Remains Tyrannical

Earlier this year, the Drug Enforcement Agency (DEA) announced that it would move marijuana from Schedule I to Schedule III under the Controlled Substances Act (CSA), greatly reducing the restrictions on the drug. It represents a historic change in federal marijuana policy and a watershed moment for generations of activists that have sought legalization on a national level. While many advocates believe the shift bodes well for efforts to relax controls on other Schedule I drugs—including promising psychedelics like psilocybin, MDMA, and LSD– Vanderbilt Law professor Robert Mikos argues that the marijuana rescheduling decision will not pave the way for rescheduling any other drug. Mikos explains that the decision preserves the barriers that make it virtually impossible to remove drugs from Schedule I. He labels those barriers the “tyrannies of scheduling.” In his paper “Marijuana and the Tyrannies of Scheduling,” forthcoming in Fordham Law Review, Mikos lays out the core challenges posed by the existing scheduling process and offers a solution that would lead to “more rational scheduling decisions that better reflect the benefits and dangers of controlled substances, as Congress intended.” The Role of Currently Accepted Medical Use in Scheduling Decisions The CSA creates five Schedules (I-V). Scheduling dictates how a drug is regulated under the statute. Schedule I drugs are subject to the most restrictive controls, and those controls are steadily relaxed as one moves down the schedules. Congress made all the initial scheduling decisions when it passed the CSA in 1970, but it also empowered the DEA, working in conjunction with the Department of Health and Human Services (HHS), to reschedule drugs based on new information acquired after the passage of the statute. Agency scheduling decisions are supposed to be based on three core characteristics of a drug: its abuse potential, its dependence liability, and whether it has a currently accepted medical use (CAMU). Unfortunately, these characteristics do not always suggest the same schedule for a drug. But as Mikos explains, the DEA has grossly simplified the scheduling process by suggesting that CAMU determinations should trump all other considerations. In particular, the agency has insisted that a drug with no CAMU must be placed on Schedule I, regardless of its abuse potential or dependence liability. According to Mikos, the DEA’s simplification of the scheduling process places tremendous weight on agency CAMU determinations and how the agency chooses to define this particular scheduling criteria. The Tyranny of Science In the past, the DEA insisted that the only way to demonstrate that a drug has a CAMU was by completing multiple controlled trials (RCTs) demonstrating that a drug is effective at treating some medical indication, the same requirement for new drug approval under the Food, Drug and Cosmetic Act. As Mikos has noted in his past work, completing such trials is “notoriously expensive and time-consuming,” requiring strict parameters and a large number of participants. The challenge is even more daunting for drugs already on Schedule I, because the CSA restricts research on such drugs. Due to regulatory restrictions, marijuana advocates have struggled to complete even a single RCT demonstrating marijuana’s medical efficacy. Indeed, in the past 50 years, only one Schedule I drug (Epidiolex) has ever been able to satisfy the DEA’s CAMU test, leading Mikos to label the agency’s science-focused approach the “Tyranny of Science.” The Tyranny of the Majority In 2023, however, HHS devised an alternative CAMU test that emphasizes practical experience over scientific research. “Because more than 30,000 health care practitioners (HCPs) had already recommended the drug to their patients in the thirty-eight states with medical marijuana laws,” Mikos explains, “the agency concluded there was enough clinical experience to demonstrate that marijuana has a CAMU and thus could be rescheduled.” But while this alternative test does not require completing RCTs – and thereby eliminates the Tyranny of Science – Mikos demonstrates that it is no less tyrannical than the DEA’s original CAMU test. According to Mikos, the alternative CAMU test simply “imposes a different form of tyranny: the Tyranny of the Majority.” He explains that to accumulate the clinical experience needed to satisfy the new test, advocates must convince popular majorities in a substantial number of states to legalize medical use of a drug. It took decades to build the public support necessary to do that for marijuana, and Mikos points out that no other Schedule I drug currently commands the same level of public support as marijuana. “Despite growing interest in the therapeutic value of [psychedelics, . . . less than a quarter of all Americans support legalizing psychedelics like psilocybin,” Mikos writes. “By comparison, 90% of Americans support legalizing medical marijuana.” What is more, even if large numbers of states were to legalize medical use of a substance like psilocybin or MDMA, advocates will also have to convince large numbers of patients, their health care practitioners (HCPs), and their suppliers to risk federal sanctions in order to accumulate the clinical experience HHS demands to satisfy the new CAMU test. “While marijuana was finally able to run the gauntlet, no other Schedule I is likely to replicate that feat anytime soon. Other promising Schedule I drugs like psilocybin, MDMA, and LSD are likely to remain trapped on that schedule for the foreseeable future,” the paper states. A New Way Forward Mikos argues that the agencies did not need to create a new CAMU test to reschedule marijuana. He suggests that the DEA has placed too much emphasis on CAMU in scheduling decisions. The DEA “has no authority, and no good reason, to hold (or place) a drug on Schedule I solely because the drug lacks a currently accepted medical use.” Indeed, Mikos suggests the agency’s emphasis on CAMU runs contrary to the text of the CSA and provides insufficient information about a drug’s benefits and risks to make sensible scheduling decisions. Rather than propose yet another, less tyrannical CAMU test, Mikos suggests that the DEA should instead take a more flexible approach to scheduling, one that considers all 3 criteria – a drug’s abuse potential, its dependence liability, and whether or not it has a currently accepted medical use (CAMU)—to determine where a drug belongs among the statute’s five schedules. “Although my approach would not make it any easier to demonstrate CAMU, it would reduce the dominant influence CAMU determinations now wield over scheduling decisions,” Mikos concludes. It would enable the agency to remove drugs like marijuana, psilocybin, or MDMA from Schedule I, even if they lack a currently accepted medical use, if their abuse potential and dependence liability so warrant. “As a result,” he notes, “my approach would foster more rational administrative scheduling decisions going forward.”

3 min

FTC Chair Commends Vanderbilt Policy Accelerator Initiative for Research on Policies to Help Govern AI

The Vanderbilt Policy Accelerator for Political Economy and Regulation (VPA) is leading the way in research and policy recommendations on the governance of artificial intelligence. At the Third Annual Networks, Platforms & Utilities conference hosted by the VPA in June, the groundbreaking initiative was commended by FTC Chair Lina Khan for its impact on her work with the agency. As part of Discovery Vanderbilt, Vanderbilt Policy Accelerator for Political Economy and Regulation is a groundbreaking initiative to bolster innovative research and education at Vanderbilt. The mission of VPA is to swiftly develop and advance cutting-edge research, education and policy proposals at a pace that aligns with the urgency of today’s challenges. The VPA encompasses several projects, including one dedicated to revitalizing the study of the law and political economy of networks platforms, and utilities (NPUs) in transportation, communications, energy and banking. “Many of our country’s most pressing economic and social challenges are directly tied to how we govern network, platform, and utility industries, including airline flight cancellations, social media regulation, banking failures and electric grid crashes,” said Ganesh Sitaraman, the New York Alumni Chancellor’s Chair in Law at Vanderbilt Law School and director of VPA. VPA’s Project on Networks, Platforms and Utilities has developed a series of papers and policy proposals to improve the governance of these sectors. Among this work are a set of proposals to policymakers for regulating air travel, a plan for stabilizing and regulating the banking sector, and 40 recommendations to promote competition throughout the American economy. With growing interest in AI, VPA has turned its eye to how policymakers can address the harms that come from concentration in the AI technology stack. VPA’s papers have developed an antimonopoly approach to regulating AI, addressed public capacity for AI, and offered proposals on federal procurement of AI resources. VPA’s work in this field has gotten increasing attention. VPA director Ganesh Sitaraman participated in one of the U.S. Senate’s AI Fora in 2023. And during the Third Annual Networks, Platforms & Utilities conference hosted by the VPA in June, FTC Chair Lina Khan specifically noted VPA’s impact on the agency. “I think the work that VPA has been doing on AI has been so enormously useful,” said Khan. “It’s really striking how it took 15 years before the NPU toolkit was even discussed alongside the Web 2.0 giants. So, the fact that from the very get-go this kind of framework is being applied in the context of AI policy discussions really marks that forward movement.” During the June conference, participants—which included 64 attendees from 15 different countries— discussed how their jurisdictions of study approach the regulation of network, platform and utility industries. This year’s conference was structured around eight panels, one on general themes and seven featuring a specific NPU sector: railroads, electricity, banking & finance, airlines, social infrastructure, tech platforms and telecommunications. “Vanderbilt is a leader in research on these topics, and we were very excited to welcome scholars from around the world to Nashville and to Vanderbilt, in order to explore these issues from a comparative and global perspective,” said Sitaraman. In the coming months, the conference organizers intend to compile the papers presented at the conference into an edited volume. To learn more, visit the Vanderbilt Policy Accelerator website.

View all posts