Alexandre Bayen is the Liao-Cho Professor of Engineering at the University of California Berkeley and director of its Institute of Transportation Studies. Bayen plays leading roles in multiple transportation projects.
Courtesy of Alexandre Bayen

Alexandre Bayen is a driving force behind mixed-autonomy traffic

Coordinated automation could improve traffic flow, boost efficiency, and slash emissions. A combination of machine learning, big data, and Amazon Web Services is making this future possible.

The smooth-flowing traffic of the future is just around the corner. Advances in vehicle automation are converging with developments in machine learning (ML) and cloud computing to create self-driving vehicles that not only control themselves safely, but also have an oversized beneficial effect on the journeys of all the regular drivers on the road around them. Welcome to “mixed autonomy traffic”.

Leading the pack into this future is Alexandre Bayen, the Liao-Cho Professor of Engineering at the University of California Berkeley and director of its Institute of Transportation Studies. An expert in control and optimization, Bayen is playing leading roles in multiple transportation projects, ranging from cutting-edge, open-source traffic simulation and optimization, to large scale freeway observation that involves putting automated vehicles into real traffic to explore the impact of ML-derived self-driving behaviors. These automated vehicles also have human supervisors at the wheel, ready to take over the vehicle at any time if needed.

Before delving into Bayen’s work, an example of the promise of mixed autonomy traffic is in order.

Traffic jam experiment
This video is from a 2008 experiment in which people are attempting to maintain the same speed while driving single-file around a circular track.

Anyone regularly caught in “phantom” traffic jams, which have no obvious cause, knows how annoying they are. It is simply the nature of human drivers to create these so-called “stop-and-go waves” — we just can’t help jamming up then spreading out on the road, as illustrated by a brief video (above) of a classic 2008 experiment in which people are attempting to maintain the same speed while driving single-file around a circular track.

Fast forward to 2017, to a series of similar experiments led by Bayen’s collaborators, Jonathan Sprinkle of the University of Arizona and Daniel Work of Vanderbilt University. This work echoed the 2008 experiment, but with an enormous difference: of the 20 or so cars on a circular track, one of them could switch into self-driving mode. When it did, the effect on the stop-and-go waves was immediate — and remarkable.

Self-driving cars experiment demonstrates dramatic improvements in traffic flow

Simply through the slowing or accelerating of this single car, in accordance with its traffic-optimization algorithms, the traffic waves dissipated significantly. In one test, fuel consumption of the cars in the ring was reduced by more than 40% and excessive braking events dropped from 8.5 per vehicle-kilometer to near zero.

The experimenters concluded that traffic flow control would be possible in real-life traffic with less than 5% of cars being automated.

A self-driving future

With that in mind, what will happen to our existing traffic flow when increasing numbers of vehicles are self-driving? This is the future being shaped by Bayen and his group. At the center of his work is an open-source framework called FLOW. With deep reinforcement learning at its heart, FLOW is an optimization and microsimulation tool for traffic flow. Don’t be fooled by “micro” in this context — the simulation features hundreds of thousands of vehicles on complex road systems. FLOW allows the virtual exploration of complex traffic optimization challenges on a wide variety of road set-ups.

“Traffic simulation engines have become really good, very accurate, in the last decade. And the computation required has become really tractable, mostly because of scalable cloud computing offered by Amazon Web Services and others,” says Bayen.

Deep reinforcement learning is particularly suited to developing mixed-autonomy traffic optimization because it enables simulated self-driving vehicles to try out different driving behaviors. If a set of driving policies results in lower fuel use without compromising journey time, for example, the algorithm is rewarded. “Ten years ago it was really hard to compute the outcome of experiments in simulation — and very costly. You could do a couple of intersections, and maybe a couple hundred vehicles,” says Bayen. “With the plethora of data available now, combined with the ability to do these computations very fast, it has become really quick to compute the rewards and to iterate until you get something that works very well.”

Achieving a FLOW state

Bayen is keen to clarify the primary goal of FLOW. “It’s important to differentiate between boosting energy efficiency and reducing congestion. We are not attempting to fix congestion — that is not our goal, and these would not be the right tools. We are improving the energy efficiency of traffic, which is a very different problem.”

We are not attempting to fix congestion — that is not our goal, and these would not be the right tools. We are improving the energy efficiency of traffic, which is a very different problem.
Alexandre Bayen

Indeed, in simulations, FLOW’s algorithms have a minimal effect on travel time — but a dramatic effect on the driving experience, Bayen explains. “The amount of braking is significantly reduced and the amount of acceleration — where most of the energy is burned and pollutants emitted — has been significantly reduced as well. That's the main challenge.”

In 2019, Bayen received an Amazon ML Research Award to support the development of "Applications of Deep-RL for Training Connected, Autonomous Vehicles in Mixed Environments". But even before the award, FLOW was intrinsically linked to Amazon Web Services (AWS), Bayen explains. “When we started FLOW in 2018, there were only three tools widely used for microsimulation of traffic: SUMO, Aimsun, and PTV Vissim. SUMO was an open-source platform already running on AWS, but Aimsun — now owned by Siemens Mobility — built the first instantiation of their software on the AWS cloud specifically for us,” says Bayen. “The FLOW Project was the first time anyone managed to put these three big components together: the machine learning, the cloud computing, and the simulation engine. It was historic.”

A key reason this combination is important, Sprinkle says, is big data: “For societal-scale systems to take advantage of ML, they need to take advantage of these gigantic datasets. Hosting the ML algorithms on AWS — in the same place the data are — speeds up discovery.”

The success of FLOW generated a lot of interest in Bayen’s group, including from the US government, which subsequently decided to fund the research. That is when Bayen and a broad collaboration, called the CIRCLES Consortium, was formed, with Bayen, Work, and Sprinkle among the co-principal investigators. They started working with Toyota, GM, and Nissan, to develop a proof-of-concept to demonstrate that mixed-autonomy traffic control actually works on the road. “That is what we are doing now, with the generous funding of the US Department of Energy,” says Bayen.

Part of this effort is a project called I-24 Mobility Technology Interstate Observation Network (I-24 MOTION). The CIRCLES Consortium is installing video monitoring infrastructure along six miles of I-24 in Tennessee, to gather extensive, top-quality traffic data. When completed in 2022, it will consist of 400 pole-mounted, 4k-resolution cameras. “The network is already gathering an astronomical amount of data — on the order of petabytes,” says Bayen. “It will not only provide the Tennessee Department of Transportation with a lot more operational capabilities for freeway operations, but also provide the research community with an unprecedented data set that has the potential to unveil a lot of interesting traffic features.”

Real life traffic testing

This is where the rubber hits the road. This year, the CIRCLES Consortium is deploying self-driving vehicles on that same stretch of I-24, to see how ML-derived self-driving algorithms might positively impact real-world traffic. “We’re hoping that by driving a few cars differently, it will reduce energy use for the entire stream of traffic,” says Sprinkle.

Heavy morning traffic on Highway 101 going through Silicon Valley, South San Francisco Bay Area
Alexandre Bayen says going from simulations to real-world deployment is significant. “If something runs really well in simulation, one still needs to be certain that it will transfer well to hardware and run well with real cars on real roads using imperfect data."
Sundry Photography/Getty Images

“This summer, we're doing 14 vehicles — four with automation and 10 as monitoring vehicles gathering local measurements,” says Bayen. Next year, another live deployment is planned, but with a dramatic increase in the number of automated and monitoring vehicles. 

This step from simulation to real-world deployment is more like a giant leap. “If something runs really well in simulation, one still needs to be certain that it will transfer well to hardware and run well with real cars on real roads using imperfect data. That's a big challenge,” says Bayen.

To that end, since 2016, the US National Science Foundation has funded efforts to develop the software framework that enables FLOW to be deployed on a variety of real vehicles and many different hardware platforms. The real-world deployment is a cautious, painstaking process. “We have facilities at Berkeley and Vanderbilt for low speed, and later high-speed testing, that enables us to work through the sequence of steps,” Bayen notes. “Now we’ve done this on private roads, open roads, and have progressed to freeway traffic.”  

Another challenge for this field is predicting how cars might transmit their locations in the future. There are also ongoing debates around how driver movement data will or should be collected, protected, transmitted, and shared, says Bayen. “Our job is to work on the different architectures that can support these many potential paradigms. These include fully ‘decentralized’ vehicles that do not need to talk to each other or to a central authority to improve overall traffic flow, or fully centralized, in which everybody talks to everybody. Or partially coordinated, in which cars only talk to their neighboring cars, and so on. While we wait for a public policy on this, we are developing an entire portfolio of algorithms spanning a multitude of paradigms. It's a lot of work!”

But it is work worth doing, says Bayen, because FLOW is highly scalable. “Many cities have good models of their traffic systems. Putting our software on top of it is really not difficult if those models run in AIMSUN or SUMO, two of the three major simulators. We can put such models into our framework and apply machine learning directly to it.” The cloud-based aspect is essential to this scalability. “Before the cloud became a reality in this arena, people would have a specific architecture that their traffic models would run on. But because FLOW is open source and on AWS, anyone can run it, from anywhere, including other research groups. That’s the power of the cloud.”

Work agrees: “Providing an open-source approach empowers new researchers to explore their own ideas. And using machine learning for large-scale systems is exciting because of the potential for benefits to all — even if only a few parts of the system change their behavior.” And the benefits also extend to the local and global environment, says Bayen, because the emissions per vehicle — both direct, and indirect for electric vehicles — are likely to be significantly reduced.

With the rate at which the technology of mixed-autonomy traffic is advancing, the generation of drivers hitting the roads five years from now may be confused when their parents marvel at how smooth freeway traffic is “these days”, despite the large numbers of vehicles on the road. For the rest of us, knowing that phantom jams’ days are numbered will probably make them easier to bear. Honk if you disagree.

Related content

US, NY, New York
We are looking for detail-oriented, organized, and responsible individuals who are eager to learn how to work with large and complicated data sets. Some knowledge of econometrics, as well as basic familiarity with Python is necessary, and experience with SQL and UNIX would be a plus. These are full-time positions at 40 hours per week, with compensation being awarded on an hourly basis. You will learn how to build data sets and perform applied econometric analysis at Internet speed collaborating with economists, scientists, and product managers. These skills will translate well into writing applied chapters in your dissertation and provide you with work experience that may help you with placement. Roughly 85% of previous cohorts have converted to full time economics employment at Amazon. If you are interested, please send your CV to our mailing list at
FR, Clichy
The role can be based in any of our EU offices. Amazon Supply Chain forms the backbone of the fastest growing e-commerce business in the world. The sheer growth of the business and the company's mission "to be Earth’s most customer-centric company” makes the customer fulfillment business bigger and more complex with each passing year. The EU SC Science Optimization team is looking for a Science leader to tackle complex and ambiguous forecasting and optimization problems for our EU fulfillment network. The team owns the optimization of our Supply Chain from our suppliers to our customers. We are also responsible for analyzing the performance of our Supply Chain end-to-end and deploying Statistics, Econometrics, Operations Research and Machine Learning models to improve decision making within our organization, including forecasting, planning and executing our network. We work closely with Supply Chain Optimization Technology (SCOT) teams, who own the systems and the inputs we rely on to plan our networks, the worldwide scientific community, and with our internal EU stakeholders within Supply Chain, Transportation, Store and Finance. The ideal candidate has a well-rounded-technical/science background as well as a history of leading large projects end-to-end, and is comfortable in developing long term research strategy while ensuring the delivery of incremental results in an ever-changing operational environment. As a Sr. Science Manager, you will lead and grow a high-performing team of data and research scientists, technical program managers and business intelligence engineers. You will partner with operations, finance, store, science and engineering leadership to identify opportunities to drive efficiency improvement in our Fulfillment Center network flows via optimization and scalable execution. As a science leader, you will not only develop optimization solutions, but also influence strategy and outcomes across multiple partner science teams such as forecasting, transportation network design, or modelling teams. You will identify new areas of investment and research and work to align roadmaps to deliver on these opportunities. This role is inherently cross-functional and requires an ability to communicate, influence and earn the trust of science, technical, operations and business leadership.
US, WA, Bellevue
We are looking for detail-oriented, organized, and responsible individuals who are eager to learn how to work with large and complicated data sets. Some knowledge of econometrics, as well as basic familiarity with Python is necessary, and experience with SQL and UNIX would be a plus. These are full-time positions at 40 hours per week, with compensation being awarded on an hourly basis. You will learn how to build data sets and perform applied econometric analysis at Internet speed collaborating with economists, scientists, and product managers. These skills will translate well into writing applied chapters in your dissertation and provide you with work experience that may help you with placement. Roughly 85% of previous cohorts have converted to full time economics employment at Amazon. If you are interested, please send your CV to our mailing list at Key job responsibilities Estimate econometric models using large datasets. Must know SQL and Matlab.
US, WA, Seattle
The AWS AI Labs team has a world-leading team of researchers and academics, and we are looking for world-class colleagues to join us and make the AI revolution happen. Our team of scientists have developed the algorithms and models that power AWS computer vision services such as Amazon Rekognition and Amazon Textract. As part of the team, we expect that you will develop innovative solutions to hard problems, and publish your findings at peer reviewed conferences and workshops. AWS is the world-leading provider of cloud services, has fostered the creation and growth of countless new businesses, and is a positive force for good. Our customers bring problems which will give Applied Scientists like you endless opportunities to see your research have a positive and immediate impact in the world. You will have the opportunity to partner with technology and business teams to solve real-world problems, have access to virtually endless data and computational resources, and to world-class engineers and developers that can help bring your ideas into the world. Our research themes include, but are not limited to: few-shot learning, transfer learning, unsupervised and semi-supervised methods, active learning and semi-automated data annotation, large scale image and video detection and recognition, face detection and recognition, OCR and scene text recognition, document understanding, 3D scene and layout understanding, and geometric computer vision. For this role, we are looking for scientist who have experience working in the intersection of vision and language. We are located in Seattle, Pasadena, Palo Alto (USA) and in Haifa and Tel Aviv (Israel).
US, WA, Seattle
Amazon Prime Video is changing the way millions of customers enjoy digital content. Prime Video delivers premium content to customers through purchase and rental of movies and TV shows, unlimited on-demand streaming through Amazon Prime subscriptions, add-on channels like Showtime and HBO, and live concerts and sporting events like NFL Thursday Night Football. In total, Prime Video offers nearly 200,000 titles and is available across a wide variety of platforms, including PCs and Macs, Android and iOS mobile devices, Fire Tablets and Fire TV, Smart TVs, game consoles, Blu-ray players, set-top-boxes, and video-enabled Alexa devices. Amazon believes so strongly in the future of video that we've launched our own Amazon Studios to produce original movies and TV shows, many of which have already earned critical acclaim and top awards, including Oscars, Emmys and Golden Globes. The Global Consumer Engagement team within Amazon Prime Video builds product and technology solutions that drive customer activation and engagement across all our supported devices and global footprint. We obsess over finding effective, programmatic and scalable ways to reach customers via a broad portfolio of both in-app and out-of-app experiences. We would love to have you join us to build models that can classify and detect content available on Prime Video. We need you to analyze the video, audio and textual signal streams and improve state-of-art solutions while being scalable to Amazon size data. We need to solve problems across many cultures and languages, working alongside an operations team generating labels across many languages to help us achieve these goals. Our team consistently strives to innovate, and holds several novel patents and inventions in the motion picture and television industry. We are highly motivated to extend the state of the art. As a member of our team, you will apply your deep knowledge of Computer Vision and Machine Learning to concrete problems that have broad cross-organizational, global, and technology impact. Your work will focus on addressing fundamental computer vision models like video understanding and video summarization in addition to building appropriate large scale datasets. You will work on large engineering efforts that solve significantly complex problems facing global customers. You will be trusted to operate with independence and are often assigned to focus on areas with significant impact on audience satisfaction. You must be equally comfortable with digging in to customer requirements as you are drilling into design with development teams and developing production ready learning models. You consistently bring strong, data-driven business and technical judgment to decisions. You will work with internal and external stakeholders, cross-functional partners, and end-users around the world at all levels. Our team makes a big impact because nothing is more important to us than pleasing our customers, continually earning their trust, and thinking long term. You are empowered to bring new technologies and deep learning approaches to your solutions. We embrace the challenges of a fast paced market and evolving technologies, paving the way to universal availability of content. You will be encouraged to see the big picture, be innovative, and positively impact millions of customers. This is a young and evolving business where creativity and drive will have a lasting impact on the way video is enjoyed worldwide.
US, CA, Palo Alto
Join a team working on cutting-edge science to innovate search experiences for Amazon shoppers! Amazon Search helps customers shop with ease, confidence and delight WW. We aim to transform Search from an information retrieval engine to a shopping engine. In this role, you will build models to generate and recommend search queries that can help customers fulfill their shopping missions, reduce search efforts and let them explore and discover new products. You will also build models and applications that will increase customer awareness of related products and product attributes that might be best suited to fulfill the customer needs. Key job responsibilities On a day-to-day basis, you will: Design, develop, and evaluate highly innovative, scalable models and algorithms; Design and execute experiments to determine the impact of your models and algorithms; Work with product and software engineering teams to manage the integration of successful models and algorithms in complex, real-time production systems at very large scale; Share knowledge and research outcomes via internal and external conferences and journal publications; Project manage cross-functional Machine Learning initiatives. About the team The mission of Search Assistance is to improve search feature by reducing customers’ effort to search. We achieve this through three customer-facing features: Autocomplete, Spelling Correction and Related Searches. The core capability behind the three features is backend service Query Recommendation.
US, CA, Palo Alto
Amazon is investing heavily in building a world class advertising business and we are responsible for defining and delivering a collection of self-service performance advertising products that drive discovery and sales. Our products are strategically important to our Retail and Marketplace businesses driving long term growth. We deliver billions of ad impressions and millions of clicks daily and are breaking fresh ground to create world-class products. We are highly motivated, collaborative and fun-loving with an entrepreneurial spirit and bias for action. With a broad mandate to experiment and innovate, we are growing at an unprecedented rate with a seemingly endless range of new opportunities. The Ad Response Prediction team in Sponsored Products organization build advanced deep-learning models, large-scale machine-learning (ML) pipelines, and real-time serving infra to match shoppers’ intent to relevant ads on all devices, for all contexts and in all marketplaces. Through precise estimation of shoppers’ interaction with ads and their long-term value, we aim to drive optimal ads allocation and pricing, and help to deliver a relevant, engaging and delightful ads experience to Amazon shoppers. As the business and the complexity of various new initiatives we take continues to grow, we are looking for energetic, entrepreneurial, and self-driven science leaders to join the team. Key job responsibilities As a Principal Applied Scientist in the team, you will: Seek to understand in depth the Sponsored Products offering at Amazon and identify areas of opportunities to grow our business via principled ML solutions. Mentor and guide the applied scientists in our organization and hold us to a high standard of technical rigor and excellence in ML. Design and lead organization wide ML roadmaps to help our Amazon shoppers have a delightful shopping experience while creating long term value for our sellers. Work with our engineering partners and draw upon your experience to meet latency and other system constraints. Identify untapped, high-risk technical and scientific directions, and simulate new research directions that you will drive to completion and deliver. Be responsible for communicating our ML innovations to the broader internal & external scientific community.
US, CA, Palo Alto
We’re working to improve shopping on Amazon using the conversational capabilities of large language models, and are searching for pioneers who are passionate about technology, innovation, and customer experience, and are ready to make a lasting impact on the industry. You'll be working with talented scientists, engineers, and technical program managers (TPM) to innovate on behalf of our customers. If you're fired up about being part of a dynamic, driven team, then this is your moment to join us on this exciting journey!"?
US, CA, Santa Clara
AWS AI/ML is looking for world class scientists and engineers to join its AI Research and Education group working on foundation models, large-scale representation learning, and distributed learning methods and systems. At AWS AI/ML you will invent, implement, and deploy state of the art machine learning algorithms and systems. You will build prototypes and innovate on new representation learning solutions. You will interact closely with our customers and with the academic and research communities. You will be at the heart of a growing and exciting focus area for AWS and work with other acclaimed engineers and world famous scientists. Large-scale foundation models have been the powerhouse in many of the recent advancements in computer vision, natural language processing, automatic speech recognition, recommendation systems, and time series modeling. Developing such models requires not only skillful modeling in individual modalities, but also understanding of how to synergistically combine them, and how to scale the modeling methods to learn with huge models and on large datasets. Join us to work as an integral part of a team that has diverse experiences in this space. We actively work on these areas: * Hardware-informed efficient model architecture, training objective and curriculum design * Distributed training, accelerated optimization methods * Continual learning, multi-task/meta learning * Reasoning, interactive learning, reinforcement learning * Robustness, privacy, model watermarking * Model compression, distillation, pruning, sparsification, quantization About Us Inclusive Team Culture Here at AWS, we embrace our differences. We are committed to furthering our culture of inclusion. We have ten employee-led affinity groups, reaching 40,000 employees in over 190 chapters globally. We have innovative benefit offerings, and host annual and ongoing learning experiences, including our Conversations on Race and Ethnicity (CORE) and AmazeCon (gender diversity) conferences. Amazon’s culture of inclusion is reinforced within our 14 Leadership Principles, which remind team members to seek diverse perspectives, learn and be curious, and earn trust. Work/Life Balance Our team puts a high value on work-life balance. It isn’t about how many hours you spend at home or at work; it’s about the flow you establish that brings energy to both parts of your life. We believe striking the right balance between your personal and professional life is critical to life-long happiness and fulfillment. We offer flexibility in working hours and encourage you to find your own balance between your work and personal lives. Mentorship & Career Growth Our team is dedicated to supporting new members. We have a broad mix of experience levels and tenures, and we’re building an environment that celebrates knowledge sharing and mentorship. Our senior members enjoy one-on-one mentoring and thorough, but kind, code reviews. We care about your career growth and strive to assign projects based on what will help each team member develop into a better-rounded engineer and enable them to take on more complex tasks in the future.
US, WA, Seattle
Do you want to join an innovative team of scientists who use machine learning to help Amazon provide the best experience to our Selling Partners by automatically understanding and addressing their challenges, needs and opportunities? Do you want to build advanced algorithmic systems that are powered by state-of-art ML, such as Natural Language Processing, Large Language Models, Deep Learning, Computer Vision and Causal Modeling, to seamlessly engage with Sellers? Are you excited by the prospect of analyzing and modeling terabytes of data and creating cutting edge algorithms to solve real world problems? Do you like to build end-to-end business solutions and directly impact the profitability of the company and experience of our customers? Do you like to innovate and simplify? If yes, then you may be a great fit to join the Selling Partner Experience Science team. Key job responsibilities Use statistical and machine learning techniques to create the next generation of the tools that empower Amazon's Selling Partners to succeed. Design, develop and deploy highly innovative models to interact with Sellers and delight them with solutions. Work closely with teams of scientists and software engineers to drive real-time model implementations and deliver novel and highly impactful features. Establish scalable, efficient, automated processes for large scale data analyses, model development, model validation and model implementation. Research and implement novel machine learning and statistical approaches. Lead strategic initiatives to employ the most recent advances in ML in a fast-paced, experimental environment. Drive the vision and roadmap for how ML can continually improve Selling Partner experience. About the team Selling Partner Experience Science (SPeXSci) is a growing team of scientists, engineers and product leaders engaged in the research and development of the next generation of ML-driven technology to empower Amazon's Selling Partners to succeed. We draw from many science domains, from Natural Language Processing to Computer Vision to Optimization to Economics, to create solutions that seamlessly and automatically engage with Sellers, solve their problems, and help them grow. Focused on collaboration, innovation and strategic impact, we work closely with other science and technology teams, product and operations organizations, and with senior leadership, to transform the Selling Partner experience.