Self-driving cars navigate unpaved country roads map-free, thanks to array of sensors
Image credit: DT
MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) has developed MapLite, a new framework that allows self-driving cars to drive on roads they’ve never been on before without using 3D maps.
Companies such as Google and Uber only test their self-driving car fleets in major cities where they’ve spent countless hours meticulously labelling the exact 3D positions of lanes, kerbs, off-ramps and stop signs.
However, millions of kilometres of roads in the US alone are unpaved, unlit or unreliably marked. Such streets are often much more complicated to map and see a lot less traffic, so companies are unlikely to develop 3D maps for them soon.
The MapLite framework allows cars to overcome these issues by combining widely available GPS data with a series of sensors that observe the road conditions.
The system allowed the team to autonomously drive on multiple unpaved country roads in Devens, Massachusetts, and reliably detect the road more than 30 metres in advance.
“The reason this kind of ‘map-less’ approach hasn’t really been done before is because it is generally much harder to reach the same accuracy and reliability as with detailed maps,” said CSAIL graduate student Teddy Ort.
“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.”
Existing driverless systems still rely heavily on maps, only using sensors and vision algorithms to avoid dynamic objects like pedestrians and other cars.
In contrast, MapLite uses sensors for all aspects of navigation, relying on GPS data only to obtain a rough estimate of the car’s location.
The system first sets both a final destination and what researchers call a “local navigation goal”, which has to be within view of the car.
Its perception sensors then generate a path to get to that point, using lidar to estimate the location of the road’s edges.
MapLite can do this without physical road markings by making basic assumptions about the physical properties of the road. For example, it is typically more flat than the surrounding areas, or may feature parking spots or a side road.
The team developed a system of models that are ‘parameterised’, which means that they describe multiple situations that are somewhat similar. For example, one model might be broad enough to determine what to do at intersections, or what to do on a specific type of road.
MapLite differs from other map-less driving approaches that rely more on machine learning by training on data from one set of roads and then being tested on other ones.
“At the end of the day, we want to be able to ask the car questions like, ‘How many roads are merging at this intersection?’” says Ort. “By using modelling techniques, if the system doesn’t work or is involved in an accident, we can better understand why.”
MapLite is still limited in many ways. It isn’t yet reliable enough for mountain roads, since it doesn’t account for dramatic changes in elevation. As a next step, the team hopes to expand the variety of roads that the vehicle can handle. Ultimately, they aspire to have their system reach comparable levels of performance and reliability as mapped systems, only with a much wider range.
“I imagine that the self-driving cars of the future will always make some use of 3D maps in urban areas,” Ort said. “But when called upon to take a trip off the beaten path, these vehicles will need to be as good as humans at driving on unfamiliar roads they have never seen before. We hope our work is a step in that direction.”