Alex-Bayen.jpg
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

CA, BC, Vancouver
Machine learning (ML) has been strategic to Amazon from the early years. We are pioneers in areas such as recommendation engines, product search, eCommerce fraud detection, and large-scale optimization of fulfillment center operations. The Amazon ML Solutions Lab team helps AWS customers accelerate the use of machine learning to solve business and operational challenges and promote innovation in their organization. We are looking for a passionate, talented, and inventive Applied Scientist with a strong machine learning background to help develop solutions by pushing the envelope in Time Series, Automatic Speech Recognition (ASR), Natural Language Understanding (NLU), Machine Learning (ML) and Computer Vision (CV).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. 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. As a ML Solutions Lab Applied Scientist, you are proficient in designing and developing advanced ML models to solve diverse challenges and opportunities. You will be working with terabytes of text, images, and other types of data and develop novel models to solve real-world problems. You'll design and run experiments, research new algorithms, and find new ways of optimizing risk, profitability, and customer experience. You will apply classical ML algorithms and cutting-edge deep learning (DL) approaches to areas such as drug discovery, customer segmentation, fraud prevention, capacity planning, predictive maintenance, pricing optimization, call center analytics, player pose estimation, and event detection among others. The primary responsibilities of this role are to: Design, develop, and evaluate innovative ML/DL models to solve diverse challenges and opportunities across industriesInteract with customer directly to understand their business problems, and help them with defining and implementing scalable ML/DL solutions to solve themWork closely with account teams, research scientist teams, and product engineering teams to drive model implementations and new algorithmsThis position requires travel of up to 20%.
US, WA, Seattle
Are you a Ph.D. interested in the fields of machine learning, deep learning, automated reasoning, speech, robotics, computer vision, optimization, or quantum computing? Do you enjoy diving deep into hard technical problems and coming up with solutions that enable successful products that improve the lives of people in a meaningful way? If this describes you, come join our science teams at Amazon. As an Applied Scientist, you will have access to large datasets with billions of images and video to build large-scale systems. Additionally, you will analyze and model terabytes of text, images, and other types of data to solve real-world problems and translate business and functional requirements into quick prototypes or proofs of concept. We are looking for smart scientists capable of using a variety of domain expertise to invent, design, evangelize, and implement state-of-the-art solutions for never-before-solved problems.
US, WA, Seattle
Amazon internships are full-time (40 hours/week) for 12 consecutive weeks with start dates in May - July 2023. Our internship program provides hands-on learning and building experiences for students who are interested in a career in hardware engineering. This role will be based in Seattle, and candidates must be willing to work in-person.Corporate Projects (CPT) is a team that sits within the broader Corporate Development organization at Amazon. We seek to bring net-new, strategic projects to life by working together with customers and evolving projects from ZERO-to-ONE. To do so, we deploy our resources towards proofs-of-concept (POCs) and pilot programs and develop them from high-level ideas (the ZERO) to tangible short-term results that provide validating signal and a path to scale (the ONE). We work with our customers to develop and create net-new opportunities by relentlessly scouring all of Amazon and finding new and innovative ways to strengthen and/or accelerate the Amazon Flywheel.CPT seeks an Applied Science intern to work with a diverse, cross-functional team to build new, innovative customer experiences. Within CPT, you will apply both traditional and novel scientific approaches to solve and scale problems and solutions. We are a team where science meets application. A successful candidate will be a self-starter comfortable with ambiguity, strong attention to detail, and the ability to work in a fast-paced, ever-changing environment. As an Applied Science Intern, you will own the design and development of end-to-end systems. You’ll have the opportunity to create technical roadmaps, and drive production level projects that will support Amazon Science. You will work closely with Amazon scientists, and other science interns to develop solutions and deploy them into production. The ideal scientist must have the ability to work with diverse groups of people and cross-functional teams to solve complex business problems.
US, IL, Chicago
MULTIPLE POSITIONS AVAILABLECompany: AMAZON.COM SERVICES LLCPosition Title: Data Scientist ILocation: Chicago, IllinoisPosition Responsibilities:Build the core intelligence, insights, and algorithms that support the real estate acquisition strategies for Amazon physical stores. Tackle cutting-edge, complex problems such as predicting the optimal location for new Amazon stores by bringing together numerous data assets, and using best-in-class modeling solutions to extract the most information out of them. Work with business stakeholders, software development engineers, and other data scientists across multiple teams to develop innovative solutions at massive scale.Amazon.com is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation #0000
US, WA, Seattle
Note that this posting is for a handful of teams within Amazon Robotics. Teams include: Robotics, Computer Vision, Machine Learning, Optimization, and more.Are you excited about building high-performance robotic systems that can perceive and learn to help deliver for customers? The Amazon Robotics team is creating new science products and technologies that make this possible, at Amazon scale. We work at the intersection of computer vision, machine learning, robotic manipulation, navigation, and human-robot interaction.Amazon Robotics is seeking broad, curious applied scientists and engineering interns to join our diverse, full-stack team. In addition to designing, building, and delivering end-to-end robotic systems, our team is responsible for core infrastructure and tools that serve as the backbone of our robotic applications, enabling roboticists, applied scientists, software and hardware engineers to collaborate and deploy systems in the lab and in the field. We will give you the tools and support you need to invent with us in ways that are rewarding, fulfilling and fun. Come join us!A day in the lifeAs an intern you will develop a new algorithm to solve one of the challenging computer vision and manipulation problems in Amazon's robotic warehouses. Your project will fit your academic research experience and interests. You will code and test out your solutions in increasingly realistic scenarios and iterate on the idea with your mentor to find the best solution to the problem.
US, WA, Seattle
Are you excited about building high-performance robotic systems that can perceive, learn, and act intelligently alongside humans? The Robotics AI team is creating new science products and technologies that make this possible, at Amazon scale. We work at the intersection of computer vision, machine learning, robotic manipulation, navigation, and human-robot interaction.The Amazon Robotics team is seeking broad, curious applied scientists and engineering interns to join our diverse, full-stack team. In addition to designing, building, and delivering end-to-end robotic systems, our team is responsible for core infrastructure and tools that serve as the backbone of our robotic applications, enabling roboticists, applied scientists, software and hardware engineers to collaborate and deploy systems in the lab and in the field. Come join us!
US, WA, Bellevue
Employer: Amazon.com Services LLCPosition: Research Scientist IILocation: Bellevue, WA Multiple Positions Available1. Research, build and implement highly effective and innovative methods in Statistical Modeling, Machine Learning, and other quantitative techniques such as operational research and optimization to deliver algorithms that solve real business problems.2. Take initiative to scope and plan research projects based on roadmap of business owners and enable data-driven solutions. Participate in shaping roadmap for the research team.3. Ensure data quality throughout all stages of acquisition and processing of the data, including such areas as data sourcing/collection, ground truth generation, data analysis, experiment, evaluation and visualization etc.4. Navigate a variety of data sources, understand the business reality behind large-scale data and develop meaningful science solutions.5. Partner closely with product or/and program owners, as well as scientists and engineers in cross-functional teams with a clear path to business impact and deliver on demanding projects.6. Present proposals and results in a clear manner backed by data and coupled with conclusions to business customers and leadership team with various levels of technical knowledge, educating them about underlying systems, as well as sharing insights.7. Perform experiments to validate the feature additions as requested by domain expert teams.8. Some telecommuting benefits available.The pay range for this position in Bellevue, WA is $136,000-$184,000 (yr); however, base pay offered may vary depending on job-related knowledge, skills, and experience. A sign-on bonus and restricted stock units may be provided as part of the compensation package, in addition to a full range of medical, financial, and/or other benefits, dependent on the position offered. This information is provided by the Washington Equal Pay Act. Base pay information is based on market location. Applicants should apply via Amazon's internal or external careers site.#0000
US, VA, Arlington
The Central Science Team within Amazon’s People Experience and Technology org (PXTCS) uses economics, behavioral science, statistics, and machine learning to proactively identify mechanisms and process improvements which simultaneously improve Amazon and the lives, well-being, and the value of work to Amazonians. We are an interdisciplinary team, which combines the talents of science and engineering to develop and deliver solutions that measurably achieve this goal. As Director for PXT Central Science Technology, you will be responsible for leading multiple teams through rapidly evolving complex demands and define, develop, deliver and execute on our science roadmap and vision. You will provide thought leadership to scientists and engineers to invent and implement scalable machine learning recommendations and data driven algorithms supporting flexible UI frameworks. You will manage and be responsible for delivering some of our most strategic technical initiatives. You will design, develop and operate new, highly scalable software systems that support Amazon’s efforts to be Earth’s Best Employer and have a significant impact on Amazon’s commitment to our employees and communities where we both serve and employ 1.3 million Amazonians. As Director of Applied Science, you will be part of the larger technical leadership community at Amazon. This community forms the backbone of the company, plays a critical role in the broad business planning, works closely with senior executives to develop business targets and resource requirements, influences our long-term technical and business strategy, helps hire and develop engineering leaders and developers, and ultimately enables us to deliver engineering innovations.This role is posted for Arlington, VA, but we are flexible on location at many of our offices in the US and Canada.
US, VA, Arlington
Employer: Amazon.com Services LLCPosition: Data Scientist IILocation: Arlington, VAMultiple Positions Available1. Manage and execute entire projects or components of large projects from start to finish including data gathering and manipulation, synthesis and modeling, problem solving, and communication of insights and recommendations.2. Oversee the development and implementation of data integration and analytic strategies to support population health initiatives.3. Leverage big data to explore and introduce areas of analytics and technologies.4. Analyze data to identify opportunities to impact populations.5. Perform advanced integrated comprehensive reporting, consultative, and analytical expertise to provide healthcare cost and utilization data and translate findings into actionable information for internal and external stakeholders.6. Oversee the collection of data, ensuring timelines are met, data is accurate and within established format.7. Act as a data and technical resource and escalation point for data issues, ensuring they are brought to resolution.8. Serve as the subject matter expert on health care benefits data modeling, system architecture, data governance, and business intelligence tools. #0000
US, TX, Dallas
Employer: Amazon.com Services LLCPosition: Data Scientist II (multiple positions available)Location: Dallas, TX Multiple Positions Available:1. Assist customers to deliver Machine Learning (ML) and Deep Learning (DL) projects from beginning to end, by aggregating data, exploring data, building and validating predictive models, and deploying completed models to deliver business impact to the organization;2. Apply understanding of the customer’s business need and guide them to a solution using AWS AI Services, AWS AI Platforms, AWS AI Frameworks, and AWS AI EC2 Instances;3. Use Deep Learning frameworks like MXNet, PyTorch, Caffe 2, Tensorflow, Theano, CNTK, and Keras to help our customers build DL models;4. Research, design, implement and evaluate novel computer vision algorithms and ML/DL algorithms;5. Work with data architects and engineers to analyze, extract, normalize, and label relevant data;6. Work with DevOps engineers to help customers operationalize models after they are built;7. Assist customers with identifying model drift and retraining models;8. Research and implement novel ML and DL approaches, including using FPGA;9. Develop computer vision and machine learning methods and algorithms to address real-world customer use-cases; and10. Design and run experiments, research new algorithms, and work closely with engineers to put algorithms and models into practice to help solve customers' most challenging problems.11. Approximately 15% domestic and international travel required.12. Telecommuting benefits are available.#0000