Self-driving cars for country roads
Today’s autonomous vehicles require detailed 3-D maps, but a novel system enables navigation with just GPS and sensors.
Companies such as Google only test their autonomous vehicles in major cities - where they have spent countless hours meticulously recording the exact 3-D positions of the likes of lanes, curbs, ramps and stop-signs.
The Director of the US MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) explains: '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. The need for dense 3-D maps limits the places where self-driving cars can operate.'
So, if one lives along the millions of miles of roads that are unpaved, unlit or unreliably marked, one cannot use autonomous driving. Such roads are often much more complicated to map, and get a lot less traffic - so companies have little incentive to develop 3-D maps for them.
In a first step to overcome the problem, CSAIL have developed 'MapLite' - a framework that allows self-driving cars to drive on roads that they have never been on before; and without 3-D maps.
MapLite combines basic GPS data that can be found on Google Maps with a series of sensors that observe the road conditions. Combined, these two elements permitted the team to autonomously drive on multiple unpaved country roads, reliably detecting the road more than 100 ft ahead. In collaboration with the Toyota Research Institute, the researchers used a Toyota Prius car that they fitted with a range of light detection and ranging (LIDAR) and inertial measurement unit (IMU) sensors.
A leading author of a related paper on the system states: '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. 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 its 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', 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 how the road will be relatively more flat than surrounding areas.
The team admit that MapLite still has some limitations - for example, it is not yet reliable enough for use on mountain roads, as it does not account for dramatic changes in elevation. As a next step, they hope to expand the variety of roads that the vehicle can handle, ultimately aspiring to have the system reach comparable levels of performance and reliability as mapped systems - but with a much wider range.
The CSAIL Director concludes: 'I imagine that the self-driving cars of the future will always make some use of 3-D maps in urban areas. 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.'
Details from the MIT link below . .
Image from CSAIL