A technology being developed at Stanford University in Palo Alto, CA is likely to bring autonomous cars closer to road-ready status. Though most states, cities, and other municipalities have yet to put their trust in autonomous technology by legalizing its use, technology such as the kind being developed at Stanford could mean that autonomous vehicles will one day be more anticipatory, safer drivers than humans.
The laser-driven imaging technology will provide the ability for vehicles to determine what lies beyond the traditional line of sight, whether it be children playing, a car barreling toward a red light, or even a squirrel darting aimlessly toward traffic.
We [have] developed an imaging technique to see objects hidden from view by treating walls as diffuse mirrors,” said Matthew O’Toole, a postdoctoral fellow in computational imaging at Stanford University. “Like Lidar, we estimate shape by sending pulses of light into an environment and measuring the time required for the light to return to a sensor. Unlike Lidar, we also capture the light that scatters off a visible wall and interacts with objects hidden from view.
All this information allows the system to determine the shape of the object which is hidden from sight, and near-constant scanning means that its movements can be tracked as well. Once the sensors capture the laser frequencies which have been sent out and return to the sensors, the Stanford team’s unique algorithm will interpret those pulses to provide an image to the computers.
While the concept of using lasers and sensors to determine the shape of unseen objects is not completely new, the Stanford team’s algorithm is more advanced than its predecessors. They have refined the system to cancel out unwanted images that result from scattered pulses capturing non-desired items once they bounce off the target object.
There is this preconceived notion that you can’t image objects that aren’t already directly visible to the camera – and we have found ways to get around these types of limiting situations, O’Toole added.
The development and further perfection of technologies such as the one created in Stanford’s laboratories only accelerate the period which lies before the full-blown adoption of autonomous vehicles in smart cities.