How May Mobility Uses Imagination to Drive Innovation

Giving our Autonomous Vehicles the Power of Choice

It’s fairly straightforward to tell an autonomous vehicle (AV) how to respond to specific situations it might encounter on the road. In situation 1, do X. In situation 2, do Y. The challenge comes from the number of situations that an AV might encounter. Will the AV do the right thing in situation 43,768?

At May Mobility, one of our key technologies is Multi-Policy Decision Making (MPDM). MPDM is our way of reframing the challenge: instead of telling the vehicle when to do what (which is hopeless), we give the vehicle options and let it decide for itself which option is best.

In a sense, we’re giving our AV’s an imagination.

The image shows a May Mobility employee demonstrating an MPDM maneuver on their desktop.

Sajan Patel, Senior Robotics Engineer at May Mobility, demonstrates a particular driving scenario using MPDM.

By giving our AV’s an imagination– the ability to imagine what might happen if it does X, or if it does Y, we can simulate the likely outcome of X (perhaps “pass the car in front of us”) versus the likely outcome of Y (perhaps “follow the slow car”). This imagination makes it much easier to determine whether X or Y is the better option. MPDM is not making decisions at the individual “action” level– for example gas/brake/steer, or specific trajectories that our car will follow. In contrast, each policy that we choose between is a driving strategy that can adapt its behavior in response to what other road users are doing.

It’s fair to say that every AV company does simulation offline. Their reason for doing so is to measure the quality of their AV software. May Mobility has differentiated our approach by doing simulation online; simulation that accounts for the actions and responses of our AVs to what’s taking place on the road is very different. Understanding the way that road users interact with each other is absolutely critical to driving well.

In this gif, the green rectangle is a May Mobility autonomous shuttle simulating how it could maneuver around the green and purple polygon, which is a parked vehicle in front of it. The vehicle behind it (yellow polygon) is making a left turn from behind the May shuttle. The different lines shooting out of each agent show their various future trajectories as simulated by MPDM, and the darker the trajectory, the more likely that future outcome will occur.

To achieve online simulations that enable an AV to imagine outcomes, the MPDM simulator on our vehicles has to be extremely fast. For example, MPDM runs tens of thousands of times faster than real-time, which allows May to imagine different future outcomes. We can vary both our AVs strategies as well as the strategies of other road users. No single simulation is right, but by simulating enough possible scenarios, we can decide whether strategy X is better/safer/more comfortable than strategy Y. And this is where things get interesting. A consequence of electing a particular policy with MPDM is that we actually don’t know what the vehicle will do. Not exactly. And of course we don’t know exactly what other road users are going to do either. It doesn’t make sense to say “here’s the trajectory I’m going to follow.” What we do have is a probabilistic characterization of the types of trajectories that a policy might generate. And that lets us pick the best/safest/most comfortable trajectory.

The gif depicts a May Mobility autonomous vehicle making a right turn.

A May Mobility autonomous vehicle uses MPDM to simulate its own behavior and the behavior of other road users as it makes a right turn.

Put in layman’s terms, everyone has experienced driving on the road with “so-so” drivers –  the ones who technically follow the rules of the road but create hazards for other road users. For example, you’re not required to make space for a vehicle merging in, but it makes the road safer for everyone if you do. When we consider the result of choosing strategy X or Y, we evaluate the safety for everyone, not just our own vehicle. And so our vehicle leaves a little more space for a bicycle or pedestrian, even if it didn’t have to.

Of course, MPDM isn’t magic, and there are still iterative opportunities that we can improve upon. Building better agent models– so our predictions are better– is a big one. Designing policies and ensuring our AVs learn them is another. The remarkable thing about our technology stack is how consistent it has been in design and intention. We’ve simply been pushing it forward along a path we imagined back in 2017, step by step.

The advantages of MPDM are huge. Instead of telling the AV when it should do what– which doesn’t scale– we let the AV imagine the outcomes itself. That leads to emergent behavior, where the vehicle can solve problems that we never considered. Our system gets smarter every time we add a new policy – we’re up to 14 now, because MPDM has more options to choose from. And that efficiency is one of the reasons why May Mobility has been able to launch in seven cities, despite being much smaller than most AV companies. Technology matters and we’re proving it every day.

All you need is a little bit of imagination.

To learn more about MPDM, you can watch our introductory video here.

May Mobility Announces On-Demand Autonomous Service In Grand Rapids, Michigan

New service zone introduces flexible, dynamic AV rides for residents.

 

ANN ARBOR, Mich.Aug. 10, 2021 /PRNewswire/ — May Mobility, a leader in autonomous vehicle (AV) technology and shuttle operations, in partnership with the City of Grand RapidsVia, the leader in TransitTech, and Gentex, today announced the launch of an on-demand AV shuttle service in Grand Rapids, Michigan. The expanded, on-demand service began on July 26, 2021, as part of Phase 2 of the Grand Rapids Autonomous Vehicle Initiative (AVGR), and transitions the prior fixed route AV service into a flexible, dynamic system in a new service zone.

May Mobility’s 1.36 sq. mile service zone includes more than 20 designated pick up and drop off areas in downtown Grand Rapids.

“We look forward to continuing our partnership with the City of Grand Rapids through an expanded zone in the downtown area,” said Edwin Olson, co-founder and CEO of May Mobility. “The new service allows us to explore transportation needs in new areas of the community and provides additional opportunities for people to experience safer, greener, more accessible transportation through autonomous mobility.”

The on-demand service, which includes four May Mobility Lexus RX450h vehicles and one wheelchair-accessible Polaris GEM equipped with May Mobility’s autonomous technology, operates within a 1.36 sq. mile service zone that includes more than 20 designated pick up and drop off areas in downtown Grand Rapids. The May Mobility AV shuttles are free to ride and operate Monday – Friday from 7am – 7 pm.

May Mobility’s new on-demand service includes four May Mobility Lexus RX450h vehicles and one wheelchair-accessible Polaris GEM equipped with May Mobility’s autonomous technology.

“The City of Grand Rapids has enjoyed its partnership with May Mobility to provide innovative mobility options through the Grand Rapids Autonomous Vehicle Initiative. We look forward to embarking on this next phase together and support continued development of autonomous mobility technology while providing another equitable mobility option to connect underserved neighborhoods in Ward 1 to the downtown area,” said Justin Kimura, the Assistant Director of Mobile GR.

Transitioning to “On Demand”
May Mobility has adopted Via’s autonomous fleet platform to power booking, routing, passenger and vehicle assignment and identification, customer experience, and fleet management as part of their new flexible transit solution for this Grand Rapids deployment. The partners have a long-term strategy to introduce driverless on-demand shared transit systems in multiple locations. The Grand Rapids launch follows the companies’ joint RAPID autonomous vehicle service in Arlington, Texas. RAPID offers autonomous vehicle rides as part of the City of Arlington’s large on-demand public transit service with Via, and is the first-of-its kind in the US.

“In order for autonomous vehicles to reach their full potential as part of large-scale transit networks, they must be on-demand, optimally routed, and shared by multiple passengers,” said Cariann Chan, SVP of Business, Via. “We are proud to work with May Mobility to offer Via’s flexible platform to help achieve this goal, and to play a leading role in this new era of efficient and equitable transportation solutions in Grand Rapids.”

Riders can request vehicles within the designated area of service by downloading the May Mobility mobile application, which is available for both Android and iOS devices. The app shows the rider the nearest pickup location and suggested drop off location within closest proximity to their point of interest.

 

No Item Left Behind
It’s a common situation when an item such as a mobile device, a briefcase or a purse is left on public transportation and the subsequent feeling of helplessness that follows. May Mobility and Gentex are working together to integrate a data capture system with sensing pods into the May Mobility self-driving shuttles that will help the companies develop technology to track objects, monitor passenger health and safety, and keep the vehicle clean and operational.

“We’re excited to continue our partnership with May Mobility,” said Neil Boehm, Gentex chief technology officer.  “This service expansion not only provides the city with a unique, supplemental public transport hub, but also acts as a real-world laboratory for studying, evaluating, and testing various safety and convenience components necessary to better support passengers in the autonomous age.”

To celebrate the launch of the on-demand service in an adjacent service zone May Mobility and MobileGR will host demonstration rides on Aug. 24 from 10 am – 4 pm. at the YMCA Grand Rapids, 475 Lake Michigan Dr NW.

 

About May Mobility

May Mobility is a leader in autonomous vehicle technology development and deployment. With more than 275,000 autonomous rides to date, May Mobility is committed to delivering safe, efficient and sustainable shuttle solutions designed to complement today’s public transportation options. The company’s ultimate goal is to realize a world where self-driving systems make transportation more accessible and reliable, the roads safer, and encourage better land use in order to foster more green, vibrant, and livable spaces. For more information, visit maymobility.com.

 

About Gentex

Founded in 1974, Gentex Corporation (NASDAQ: GNTX) is a supplier of automatic-dimming rearview mirrors and electronics to the automotive industry, dimmable aircraft windows for aviation markets, and fire protection products to the fire protection market. Visit the company website at www.gentex.com.

 

About the City of Grand Rapids

The City of Grand Rapids provides a full range of services to residents, students and visitors. Grand Rapids is a diverse and culturally rich community of nearly 200,000 residents located along the banks of the Grand River, 30 miles east of Lake Michigan. It is the second-largest city in Michigan and serves as the county seat of Kent County and the economic engine for the western part of the state. Grand Rapids has been recognized nationally for its quality of life and named one of the 25 best places to live in the U.S. It also has been touted among the best cities to start a career, raise a family and retire, among others. Stay connected with City news, events and information at: grandrapidsmi.usfacebook.com/CityofGrandRapids , twitter.com/CityGrandRapids, and instagram.com/citygrandrapids.

 

About Via

Founded in 2012, Via pioneered the TransitTech category by using new technologies to power public mobility systems, optimizing networks of dynamic shuttles, buses, wheelchair accessible vehicles, school buses, and autonomous vehicles around the globe. Building the world’s most efficient, equitable, and sustainable transportation network for all riders — including those with limited mobility, those without smartphones, and unbanked populations — Via works with its partners to lower the cost of public transit and provide accessible options that rival the convenience of a personal car at a much reduced environmental impact. At the intersection of transportation and technology, Via is a visionary market leader that combines software innovation with sophisticated service design and operational expertise to fundamentally improve the way the world moves, with 500 global partners on six continents, and counting.