Motional: Scalable AI Solutions for Driverless Vehicles

Motional's approach to developing autonomous vehicles involves continuous learning and data sharing across the industry.

• Motional uses a continuous learning framework to mine on-road driving data and discover rare scenarios or areas where there are challenges or issues with their performance.
• They up sample and incorporate more of these scenarios into their training data to improve their autonomy performance.
• Motional recognizes the need for richer development of data sets and sharing of those data sets to fuel the development across the industry.
• They have pioneered a data sharing culture that has now extended across the industry.
• Motional's approach involves not just increasing the volume of data, but getting the right data, including finding rare objects and identifying challenging scenarios.
• Their focus is on improving their autonomy performance to achieve true driverless capability.

Motional's continuous learning framework allows them to improve their autonomy performance by discovering rare scenarios or areas where there are challenges or issues with their performance. For example, they may encounter a cyclist carrying a surfboard or unusual driving behavior around a construction zone. By mining this data and incorporating it into their training data, they can improve their overall performance and accelerate their learning process.

Motional is making autonomous vehicles a reality; it was the first company to successfully perform a cross-country autonomous drive and has launched its publicly available ride-hail services in Las Vegas via the Lyft network. In this keynote, Laura Major, Motional’s Chief Technology Officer, describes the various techniques the company uses to discover long-tail data— say, a cyclist carrying a surfboard or irregular driving patterns around construction sites—and incorporate that into both training and testing. Part of this involves combining sensor modalities including cameras, Lidar, and radar, Major explains, and it all works with Motional’s Continuous Learning Framework. Major gives a bit of a preview of what’s coming next for Modality, including meal-delivery services and its plans for global expansion. Major began her career as a cognitive engineer for Draper Laboratory, where she combined her psychology and engineering skills to design decision-making support devices for US astronauts and soldiers. Laura also spent time at Aria Insights, Inc. (formerly known as CyPhy Works), a US-based drone manufacturer that specialized in developing highly advanced drones. She served as VP of Engineering, and then Chief Technology Officer, working on the development of autonomous aerial vehicles. She co-authored the book What To Expect When You're Expecting Robots: The Future of Human-Robot Collaboration.