The Computer Science and Artificial Intelligence Laboratory, known as "CSAIL," within the Massachusetts Institute of Technology is working on a system to help driverless cars navigate roadways without relying on three-dimensional maps.
Dubbed "MapLite," it allows self-driving cars to operate on roads they have never been on before by combining what CSAIL researchers describe as "simple GPS data that you'd find on Google Maps" with a series of sensors that observe the road conditions. In tandem, those two technologies allowed a vehicle to drive autonomously on multiple unpaved country roads in Devens, Mass. – reliably detecting the road more than 100 feet in advance.
MIT noted that this project is supported by the National Science Foundation and the Toyota Research Initiative and that as part of its collaboration with the TRI, MIT's researchers used a Toyota Prius outfitted with both light imaging, detection, and ranging or "LIDAR" and inertial measurement unit or "IMU" sensors for that road test.
"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," noted CSAIL graduate student Teddy Ort, the 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."
[Side note: A recent study by AAA finds that Americans are becoming "more accepting" of autonomous vehicles. A video report detailing the findings of that study can be found below. The American Association of State Highway and Transportation Officials also sponsored an hour-plus meeting in the subject of self-driving cars back in March; a meeting
recorded by C-Span.]
Daniela Rus, director of MIT's CSAIL operation, noted that this "map-less" guidance system is crucial for helping self-driving vehicles navigate millions of miles of U.S. roads that are unpaved, unlit, or unreliably marked – especially in rural areas.
She added that 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.
"Our minimalist approach to mapping enables autonomous driving on country roads using local appearance and semantic features such as the presence of a parking spot or a side road," Rus explained.
[Below is MIT-provided video of CSAIL's new "map-less" software guiding a test drive.]
Her team also relied on a system of models that are "parameterized," 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.
Still, there are limitations to what MapLite technology can do, Rus noted. For example, it isn't yet reliable enough for mountain roads, since it doesn't account for dramatic changes in elevation, she said.
Photo: CSAIL test vehicle / MIT
The Federal Railroad Administration issued a Notice of Funding Opportunity for $500,000 in state grants on July 11 under its Railroad Safety State Participation Pilot Grant Program, made available by the Consolidated Appropriations Act of 2018.
July 13, 2018
The Federal Transit Administration opened up a Notice of Funding Opportunity on July 11 for $5 million in fiscal year 2018 grants aimed at supporting transit projects for Native American tribes and Alaska Native villagers in rural areas.
Two recent reports indicate that distracted driving remains a growing problem in the U.S. – yet one that two Northwestern states, at least, are finding can be addressed with stricter distracted driving laws.