Can LIDAR Help Autonomous Cars Drive Safely?
Posted on behalf of RizkLaw on Jun 18, 2017 in Auto Accident
To be fully autonomous, self-driving cars must identify all nearby objects correctly, have perfectly updated mapping systems, and avoid all software glitches. Nearly all companies involved in producing autonomous vehicles rely on LIDAR for vehicle navigation. Can LIDAR deliver the kind of accuracy and dependability required of self-driving cars?
LIDAR, which stands for Light Detection and Ranging, was invented soon after the 1958 invention of lasers. Using a laser, scanner, and a GPS receiver, LIDAR works by bouncing light off far-away things to precisely determine their distance and shape. Since light travels at a predictable speed of 671 million miles per hour, the time it takes for projected light to bounce off objects and return shows the distance to whatever is around the LIDAR system, typically down to a centimeter. Some LIDAR systems take millions of measurements every second. By building up a mosaic of these measurements in 360 degrees, LIDAR can paint a three-dimensional picture of the world around it.
LIDAR Used by NOAA and US Forestry Service
LIDAR is used as a surveying tool to make high-resolution maps, with applications in geography, geology, seismology, archeology, forestry, atmospheric physics, and laser guidance. The National Oceanic and Atmospheric Administration (NOAA) uses LIDAR to produce accurate shoreline maps, make digital elevation models, and to assist in emergency response operations. Because the technology can show accurate data on canopy cover, openings, and density of trees, the U.S. Forestry Service currently plans to adopt LIDAR to improve forest thinning efforts. Capabilities of LIDAR instruments vary, with the best sensors able to see details of a few centimeters at distances of more than 100 meters.
Limitations with Camera and Radar in Autonomous Vehicles
Self-driving vehicles being tested by companies such as Alphabet, Uber, and Toyota rely on LIDAR to locate themselves on the detailed maps they need to identify objects around them. Most companies in the race to commercialize self-driving cars, with the exception of Tesla, consider LIDAR essential. Tesla instead relies solely on cameras and radar. Supplementing its front-facing camera, a Tesla Model S also incorporates long-range front facing radar that can reach over 500 feet, short-range ultrasonic sensors which can detect objects up to 16 feet, and GPS. However, radar sensors can’t see much detail, and cameras don’t perform well in conditions with low light or glare. A camera lens can also get dirty or covered with snow or not see behind fogged-up glass.
LIDAR Does Not Work in All Situations
LIDAR also has limitations. It doesn’t work in fog, heavy rain, or snow. With snow on the ground, a LIDAR sensor and camera have a difficult time seeing lane markers and other markers that help a driverless car drive and change lanes safely. Even in good weather, road markings may not be visible, causing many to say that changes need to be made to the infrastructure for autonomous cars to be successful on the streets. Ford seems to have found a solution to the problem of invisible road markings with its high-resolution 3D maps that provide information about the road and what is above the road.
Driverless cars, which rely on landmarks to pinpoint themselves on the map, also struggle going over bridges. Because bridges don’t have many environmental cues like surrounding buildings, even with GPS it is hard for an autonomous car to determine where it is. Driving in cities with tall buildings, where it is difficult to receive a GPS signal, is also a problem for an autonomous vehicle, and “drop-outs” can occur. These are issues that technologists need to solve before driverless cars become completely road-ready.
Car Companies Need Safer LIDAR to Bring Self-Driving Cars to Market
Each LIDAR system includes lasers, sensors, lenses, a clock, and computer circuitry and programming to make calculations. The world’s biggest car companies are racing to incorporate LIDAR systems that are safer than human drivers and only cost a few hundred dollars per car. At the same time, companies that manufacture LIDAR have two avenues for improving their performance: amping up the power of the laser and the sensors, which is costly, or improving their capabilities so that they use tighter laser beams and less power.
“Whoever cracks the nut, to make Lidar work with a safe self-driving car, will own the market,” said roboticist Edwin Olson of the University of Michigan. “The challenge is making something work better than the human eyeball, which is hard,” Olson said. “We aren’t really there yet.”
Learn more about issues impacting safety, well-being, and justice at rizklaw.com. To schedule a confidential appointment to discuss a claim with an attorney, call (503) 245-5677 or email firstname.lastname@example.org.