New Sensor Changes the Game for Autonomous Driving

This post is also available in: עברית (Hebrew)

Autonomous vehicles require a clear view of stationary and moving objects on or around it. Lidar is one of the driving forces that help make it possible. A laser-based surveying method, Lidar builds up a depth-based image of the world by shining out laser lights and then measuring how long it takes for the reflected pulse to be bounced back to the sensor.

Recently unveiled, Velodyne’s new VLS-128 sensor set a new record by doubling the number of laser beams on its previous top-of-the-line Lidar system to a massive 128, while shrinking the overall size of the sensor by 70 percent.

By doing so, the system promises to bring a new level of resolution to the myriad applications that call for Lidar technology — from helping cars drive autonomously to mapping sites from the air.

Velodyne’s Lidar sensors are capable of producing up to 3 million data points per second, with a range of up to 300 meters and accuracy [of around] 3 [centimeters], according to digitaltrends.com.

The new VLS-128’s resolution is considerably better than its (already highly competent) predecessor. In terms of what this means for its use in the real world, Velodyne suggests that it will sideline other sensors, such as cameras and radars, that are used by current autonomous vehicles. While those other sensors will almost certainly stay a part of the next generation of self-driving cars, there’s a good chance that they will be relegated simply to acting as backup devices.

The company says they expect to start providing engineering samples to key customers by the end of the year. Production will be fully ramped up in early 2018.