Autonomous cars can drive on unknown roads with mapless navigation
Most of today’s autonomous vehicles are being tested in specific areas – typically major cities – where details of the environment have all been carefully mapped out by hand. These self-driving vehicles, say the researchers, rely heavily on these 3D maps and only use sensors and vision algorithms to avoid dynamic objects.
“The cars use these maps to know where they are and what to do in the presence of new obstacles like pedestrians and other cars,” says Daniela Rus, director of MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL). “The need for dense 3D maps limits the places where self-driving cars can operate.”
Given the difficulties in mapping roads that are unpaved, unlit, or unreliably marked, and the lack of incentives to map those that are less trafficked, say the researchers, means that “there are huge swaths of America that self-driving cars simply aren’t ready for.” The answer, they say, lies in creating autonomous systems that are advanced enough to navigate without such maps.
To address this, the researchers developed a framework – called MapLite – that allows self-driving cars to drive on roads they’ve never been on before without the benefit of 3D maps. The system combines simple GPS data of the type found on Google Maps with a series of sensors that observe the road conditions.
Using a Toyota Prius outfitted with a range of LiDAR and IMU sensors, the researchers were able to use MapLite to autonomously drive on multiple unpaved country roads in Devens, MA, and reliably detect the road more than 100 feet 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,” says CSAIL graduate student Teddy Ort, a lead author on a related paper about the system. “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.”
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 a “local navigation goal” – a location that has to be within view of the car.
The system’s perception sensors then generate a path to get to the local navigation goal, using LiDAR to estimate the location of the road’s edges. MapLite does this without physical road markings by making basic assumptions about how the road will be relatively more flat than the surrounding areas.
“Our minimalist approach to mapping,” says Rus, “enables autonomous driving on country roads using local appearance and semantic features such as the presence of a parking spot or a side road.
A system of “parameterized” models was developed describing 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. According to the researchers, 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 modeling techniques, if the system doesn’t work or is involved in an accident, we can better understand why.”
Looking ahead, the researchers hope to expand the variety of roads that the vehicle can handle, such as mountain roads, which require accounting for dramatic changes in elevation. Ultimately their goal is to have their system reach comparable levels of performance and reliability as mapped systems but 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,” says Ort. “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.”
For more, see “Autonomous Vehicle Navigation in Rural Environments without Detailed Prior Maps.”
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
