Self-Driving Golf Carts May Pave the Way For Autonomous Cars

itwbennett writes: Researchers from MIT and Singaporean universities are experimenting with self-driving golf carts that use less (and relatively cheap) gear than self-driving vehicles while relying on computation-efficient algorithms. In addition to a webcam, each cart is equipped with four single-beam LIDAR (light detection and ranging) sensors from German maker Sick that have a field of view of about 270 degrees. Two of the sensors were mounted in the cart's front and used for determining its position and obstacle detection. The other two were cheaper, shorter-range sensors and were mounted on the back corners of the cart to scan for obstacles behind and on either side of it. The cost of the sensors was still high (on the order of $30,000) but that's less than solutions used in more sophisticated robotic vehicles. (Google has used $80,000 Velodyne LIDARs on its earlier self-driving cars.) A YouTube video shows the carts traveling the winding paths of a public garden in Singapore at a leisurely 24 kilometers per hour — slow enough for the computers to process all the obstacles (mainly pedestrians and animals). The researchers envision the self-driving vehicles being used in a shared transportation system, as rental bicycles are used in many cities.

Comments

The market for this

[gila_monster]

A month ago, my department at work held a golf outing (I did not attend, but they are remarkably popular here). Over 70 people participated. Over the course of that Friday, three golf carts were rolled, one badly enough that the driver ended up with a broken arm and had to be carted to the ER.

Several engineers are now permanently banned from that course, and we may end up not having any more golf outings. So there is definitely a market for self-driving golf carts.

The downside, of course, is that they may well end up designed by the idiots who rolled them in the first place.