Exploring the future of mobility and autonomous driving
By: Marc Prioleau
Maps used in autonomous driving require entirely new levels of accuracy and latency. This is pushing the boundaries of AI and deep learning to the edge of the networks, and it’s changing how we think about maps for humans vs maps for machines. Humans have always been in between the map and the real world (or the“join” between the visual map and reality). As advances in AI and computer vision progress, humans are increasingly being removed from the equation.
At Locate, May 30–31, we’re bringing together thinkers and makers in the location space, and we’ll be exploring the challenges in creating maps for machines, especially in the context of mobility.
We can anticipate a shared future of multi-modal autonomous vehicles, from electric bicycles to smarter transportation, to self-driving ride-hailing services, all at varying levels of autonomy.
As drivers take the back seat, maps compliment cameras, LiDAR, and sensors, adding broad location context to navigate safely and efficiently. We expect autonomous vehicles to make instantaneous decisions based on real-time perception of the street side environment, traffic patterns, speed profiles, and safety data combined with navigation instructions stretching miles ahead.
“What we need is high-definition, lane-level data for the entire world, and what we’re seeing is a race to build maps live, as we use them.” -Alex Barth, VP of Business Development at Mapbox
Join us at Locate and learn about how we’re scaling a global network of embedded sensors that’s collecting 225 million miles of anonymized telemetry data each day. This “live” data feeds back into our maps and navigation, providing a real-time perspective of how people are moving around the world.
You’ll also hear from leaders in the space like Manik Gupta, VP of Product, Maps & Marketplace at Uber, Di-Ann Eisener, Director of Growth at Waze, Eran Shir, Co-founder and CEO of Nexar, and Asa Forsell, Customer Experience Manager at Rightware. They’ll share how they’re tackling issues in scalability and connectivity, real-time data collection, and the creation of new map interfaces that build on advances in front-facing cameras and augmented reality.
And if you’re up for some friendly (or not so friendly) competition, race your own autonomous Robocar at Locate. We just opened signups, and soon, we’ll launch our Donkeycar Maps SDK. More details here.
“What’s the point of DIY-ing autonomous cars if some of the smartest, biggest companies in the world are already working on this? The answer is that we can try things they can’t. Because we’re not carrying people, we can “move fast and break things” without much risk, and ideally innovate faster.” - Chris Anderson, CEO of DIY Robotics
We’re not going to make vehicles as good at driving as humans, we’re going to make them better. See you at Locate.
Maps for Machines @ Locate was originally published in Points of interest on Medium, where people are continuing the conversation by highlighting and responding to this story.