Transforming urban transportation challenges with simulation

About May Mobility

May Mobility (May) is unlocking a better life through self-driving transportation. May delivers solutions that work in today’s communities to accelerate the path toward a future where people can drive less and live more. The company’s goal is to realize a world where self-driving systems increase the reliability of transportation, make the roads much safer, and encourage better land use in order to foster more green, vibrant, and livable spaces.

Ann Arbor, MI
Employees (as of November 2020)

"By focusing on our real-world deployments, we’re able to learn what make our riders happy while also building our operational capabilities. The Applied’s team has equipped us with tools to enable this development approach that is economically viable at the same time.” 

Edwin Olson
Co-Founder and CEO, May Mobility

May Mobility operates in Grand Rapids, MI


May Mobility operates autonomous shuttle services in several US cities to complement public transportation and provide a safe, sustainable, and shared mobility solution. While their self-driving shuttles are attended by Fleet Attendants (safety drivers) today, May aims to deploy fully-autonomous vehicles in expanded geographic coverage in the future.

The safety and comfort of riders are the utmost priorities for May’s vehicles in operation. To achieve their vision for autonomous system development, May is focusing on the following areas of development:
Agile development: Resolve operational issues immediately on production vehicles
Catching regressions before deployment: Prevent regressions from entering the production vehicles before weekly and monthly software updates are shipped
Active fleet learning: Continue to improve autonomous driving capabilities by turning anomalies seen in the field into test cases for development and validation

"Applied Intuition provides simulation tools that are critical for our testing and development process.

The Applied team has been a good partner in adding features we ask for, which in turn set off the Simulation Flywheel internally.

In the future, we are planning to use simulation to better classify disengagements to validate if it was necessary for Fleet Attendants to disengage or not."

Kamil Litman
VP of Software, May Mobility

Riders in a May Mobility autonomous shuttle outfitted with Clean Shuttle enhancements for a safe, clean rider experience.


May has partnered with Applied Intuition to bring more agility and efficiency to testing the safety, comfort, and performance of their autonomous shuttle technology.
Simulation flywheel: Applied’s collaboration to deliver on May’s feature requests set off a ‘simulation flywheel’ - a test-driven approach in which development becomes faster and regressions happen less frequently as the development team runs more scenarios, test cases, and continuous integration (CI) tests
Custom observers to test comfort: Custom observers developed for May’s development team test the comfort experience of riders
Soak testing before software update: Simulation-based approach replaces traditional long soak tests done on fixed routes in the real world. Different scenarios can be created quickly to verify safety before a software update is pushed
Automated assessment of drive data: Applied’s solution programmatically finds anomalies and other events of interest from hours of drive logs collected by the fleet of vehicles and turns them into test cases for re-simulation
Continuous development: Applied’s CI system is used to identify regressions in the autonomous driving software and root causes before the new software is deployed
Faster development for new capabilities: Applied’s simulation tool supports faster algorithm development, allowing for testing new functionality such as an obstructed unprotected right-hand turn or training system parameters over a database of scenarios

"We leverage Applied's simulation tools to accelerate the pace of engineering, to catch regressions early in the dev/test/deploy cycle, and to analyze the real-world performance of the system.

We save time otherwise spent manually root causing and debugging software in the field, while also gaining detailed insights into system performance."

Sean M. Messenger
Senior Robotics Engineer, May Mobility


May Mobility has saved hours of engineering time by automatically catching regressions in simulations before the software is deployed to the fleet.
Catching regressions in simulation instead of encountering them in the real world ensures high quality rider experience.
May is able to expand to new ODDs faster as a result of incorporating simulations into May’s development cycle.

Get stories from autonomy engineers