6 scenarios self-driving cars still can't handle by Danielle Muoio on Aug 25, 2016, 9:02 AM Advertisement
 When a Tesla Model S was involved in the first fatal crash while Autopilot was activated, Tesla wrote in a blog post that the Autopilot system did not notice "the white side of the tractor trailer against a brightly lit sky, so the brake was not applied." The fatal accident is still under investigation by government regulators, but that one sentence doesn't bode too well for Tesla. It shows that despite how far autonomous technology has come, there are still some situations that are better handled by human drivers. That's not to say human drivers are perfect — more than 37,000 people die in the US each year from car crashes, according to the Association for Safe International Road Travel. As many companies working on driverless cars have noted, having autonomous vehicles on the road could drastically reduce that number. But for that to happen, driverless cars still need to improve in some key areas. SEE ALSO: This self-driving bus could radically change public transportation 1. Driverless cars struggle going over bridges.  Raffi Krikorian, Uber's engineering director, recently told Bloomberg that its driverless cars struggle going over bridges. That's because Uber has meticulously mapped roads so that the driverless car can compare what it's seeing with what is supposed to be there, helping it avoid objects and pedestrians. Because bridges don't have many environmental cues like surrounding buildings, it's hard for the Uber car to figure out where it is. GPS helps the car position itself, but not to the accuracy Uber wants.
2. Self-driving cars also struggle to "see" in inclement weather. RAW Embed "Heavy snow and rain tend to confuse LiDAR sensors and also cameras," John Dolan, principle systems scientist at Carnegie Mellon's Robotics Institute, told Business Insider. "So you end up having some problems." LiDAR refers to the light sensing radar that uses lasers to map the car's surroundings so it can "see" the world. When there's snow on the ground, the cars' LiDAR sensor and camera have a difficult time seeing the lane markers and other markers that help them drive safely. Ford made somewhat of a breakthrough in overcoming this problem when its driverless cars successfully drove in snow on a closed course. Ford created high-resolution 3D maps that come with information not only about the road, but also what's above the road, like its topography and nearby signs and landmarks. This way, when the car can't see lane markings, it can use landmarks to pinpoint itself on the map.
3. In that same vein, driverless cars struggle on roads without clear lane markings.  Tesla CEO Elon Musk vented about this problem to a group of reporters in October, according to the Washington Post. At the time, he showed the lack of clear lane markings on Interstate 405 near Los Angeles International Airport. When driverless cars can't distinguish the lanes, it makes it nearly impossible for them to drive or change lanes safely. Andrew Ng, chief scientists at Baidu, wrote in a Wired post that it will be necessary to make "modest changes to our infrastructure" for driverless cars to be successful on our streets.
See the rest of the story at Business Insider
| 
0 comments:
Post a Comment