Optimus Ride details its plans at the 2017 GPU Technology Convention in Silicon Valley

author: Eric Walz   

By Eric Walz

Optimus Ride Inc., a startup in Cambridge, Massachusetts, is developing self-driving technologies specifically for electric vehicles.The company hopes to introduce level 4 autonomy electric vehicle fleets.

In a presentation held at the 2017 GPU Technology Conference in San Jose, California on Tuesday, May 9th, the company detailed its future plans. Sertac Karaman, the Co-founder, President & Chief Scientist at Optimus Ride said his recent research is focused on developing planning and control algorithms for autonomous vehicles and autonomy-enabled transportation systems for the company.

Karaman started his self-driving efforts at MIT and entered the famed Darpa challenge in 2007, where he and his team successfully built an early self-driving vehicle. He is currently a working as a professor at MIT where he is researching autonomous technology, in addition to running Optimus Ride.

Most interestingly, Karaman introduced the audience to the concept of "parallel autonomy" as an gradual entry point to full autonomy, before fully autonomous cars are introduced.

Parallel Autonomy

Parallel autonomy is a system that will prevent the driver from controlling the car when a hazard is present, such as another vehicle or a pedestrian, yet still giving the driver control of certain, planned vehicle functions. He also referred to the system as "guardian angel autonomy".

For example, a self-driving car can be programmed to give a driver only a specific steering angle on the highway, or at higher speeds to avoid sharp, unsafe lane changes. Another use can be if a driver wanted to change lanes and another vehicle was in the way, the steering input will be disabled until the maneuver can be made safely. The technology can also be used to limit a vehicle to a safe speed.

By introducing parallel autonomy first, it can help bridge the gap between having human drivers to level 4 or 5 autonomy. Mr. Karaman explained that achieving autonomy at faster speeds requires much more precision and computing power.

High speed, high complexity is difficult to engineer for autonomous driving, while low speed, low complexity is much easier to attain. In this case, self-driving may start out on farms or rural areas in low speed low complexity environments, before being ready for crowded cities and highways.

Human controlled cars waste infrastructure

Over the course of the 20th century, wasted infrastructure was created by designing roads to eliminate stop signs, and to help vehicles merge onto highways, including building large, complex jughandles and overpasses. Mr. Karaman suggested many highway intersections can be eliminated when cars are autonomous. He added that streets were not originally made for cars in cities, especially in Boston, yet we build bigger, more complex roads to eliminate congestion. Current ground infrastructure is at capacity in most major metropolitan areas.

A typical highway intersection, built to eliminate traffic signals

One of the more interesting things Karaman said is that the car itself created the sprawl and congested roads that exists today. Because of the car, cities and growing suburbs were connected, which required more roads to be built for the cars to travel on. Then roadways became clogged with traffic as populations grew, and more cars were needed travel to and from suburbs. Many suburbs were built without considering any other transportation options other than the car.

Modern vehicles are not being used to their full potential

The top speed of a cars has increased over the years. Many cars are car capable of speeds in excess of 210 km per hour, yet congestion limits the average speed to only about 32 km in most global cities, including New York. Additionally, cars occupy 50% of available parking spots, where they remain stationary for over twelve hours per day. Karaman added that developing faster cars requiring more safety systems is a waste of engineering effort, instead the industry should focus on autonomous technology.

Potential for autonomous cars

Autonomous cars can be revolutionary, such as when the train was invented. All of the early transportation mishaps and poor urban planning of the 20th century can be reversed by the self-driving car. Self-driving vehicles may transform the transportation industry, yet society must overcome challenges that that go far beyond just technology.

About Optimus Ride

The Optimus Ride team has its roots at MIT, and collectively they share over 30 years of experience on the cutting edge research in self-driving technologies, electric vehicles, mobility-on-demand and other transportation systems. The team also includes a decade of industrial and entrepreneurial experience spanning manufacturing robots, medical robots, shared vehicle fleet management and urban design.

Building on this experience, Optimus Ride will leverage the latest advances in complex sensor fusion, mapping, computer vision and machine learning to develop its systems. The company is working to integrate these technologies in order to deploy a new form of transportation system that enables safe, sustainable and equitable mobility access.

Optimus Ride Funding

So far, Optimus Ride has raised a series seed investment of $5.25M co-led by NextView Ventures and FirstMark Capital.

This round of seed venture financing will enable Optimus Ride to accelerate the development of its fully autonomous (level 4) vehicle technology. Investors in the round include venture capital firms Greycroft Partners, Morado Venture Partners, Haystack and Uj Ventures. Optimus Ride also secured investment from NVIDIA GPU Ventures, which is the investment arm of NVIDIA, the world's leading AI computing company.

Optimus Ride is currently testing its systems in partnership with the City of Boston, and is currently engaging in additional partnerships for testing and pilot deployments to other cities in the U.S.

Eric Walz

Originally hailing from New Jersey, Eric is a automotive & technology reporter covering the high-tech industry here in Silicon Valley. He has over 15 years of automotive experience and a bachelors degree in computer science. These skills, combined with technical writing and news reporting, allows him to fully understand and identify new and innovative technologies in the auto industry and beyond. He has worked at Uber on self-driving cars and as a technical writer, helping people to understand and work with technology.