Thursday, 13 December 2018
Latest news
Main » Self-driving cars can now navigate back roads without 3D maps

Self-driving cars can now navigate back roads without 3D maps

09 May 2018

Those are the features that aren't available on a country road.

Next, the researchers will expand upon the types of roads MapLite can navigate.

Current testing of self-driving cars is limited to specific areas because companies like Google have painstakingly labeled exact 3D positions of roads, curbs, and road signs ahead of the testing. So basically if you live in an area which is unlit, unpaved, or not marked reliably then you can stop dreaming that they will be self-driving cars in your area because such streets are often complicated to plot on the map and have less traffic, there by most companies are unlikely to develop 3D maps for these areas anytime sooner.

Navigating roads less traveled in self-driving cars is a hard task.

MapLite, as they dubbed their system, uses the GPS data to get a rough estimate of where on the road the vehicle is.

"A system like this that can navigate just with on-board sensors shows the potential of self-driving cars being able to actually handle roads beyond the small number that tech companies have mapped". One reason for this is, obviously, more people will use self-driving vehicles in these areas, but it is also because these areas are so well documented.

The solution: A new, more adaptable approach by the CSAIL team, called MapLite, uses simple Global Positioning System data to plot a path to the vehicle's destination, and lidar sensors to navigate along the way. In addition, there are still few places where these vehicles can even operate.

The full paper, which you can find in the document attached below this piece, will be presented this month at the International Conference on Robotics and Automation (ICRA) in Brisbane, Australia.

However, if you were to move through the world like most self-driving cars, you'd essentially be staring at your phone the whole time you're walking.

The auto then uses LIDAR to estimate where the edges of the road are based on the assumption that the road is relatively flat compared to the rest of its surroundings.

"At the end of the day we want to be able to ask the auto questions like 'how many roads are merging at this intersection?'" says Ort. The system first sets both a final destination and what researchers call a "local navigation goal", which has to be within view of the vehicle. Those elements work together to allow the test vehicle to autonomously drive on multiple unpaved roads in Devens, Massachusetts.

The vehicle used by the team was a Toyota Prius that was fitted with a range of LIDAR and IMU sensors. Eventually, their aim is to make their system achieve comparable levels of reliability and performance as mapped systems, however with a considerably broader range. The technology still can't account for all possible variables, though, including the dramatic changes in elevation that occur on mountain roads.

"I imagine that the self-driving cars of the future will always make some use of 3-D maps in urban areas", said Ort. The technology is far from ideal but it seems like a step in the right direction for self-driving cars in the future.

This project was supported, in part, by the National Science Foundation and the Toyota Research Initiative.

Self-driving cars can now navigate back roads without 3D maps