Robot forklifts can find their own way around

March 22, 2007
The National Institute of Standards and Technology (NIST) is developing advanced sensor-processing and modeling algorithms to help robot forklifts verify the location and orientation of pallets laden with goods.

The corresponding 3D point cloud view shows a man and a pallet from less than 3 m away and lower than 10 m in height from the sensor.

Two onboard, single-scan-line ladar devices negotiate obstacles and locate pallets. Ladar — laser detection and ranging — measures properties of reflected lasers to determine range and other information about the target. A sensor at the base of the automatic-guided vehicle (AGV) detects obstacles such as humans in the forklift's path. It also scans inside trucks to detect pallets and measure the distance between forklifts and the side of the truck.

The Panner, the other sensor, is a rotating, panning laser ranger on top of the automatic-guided vehicle (AGV). It acquires scan lines of range data to reconstruct the scene in visual formats such as a colored-coded image (where colors indicate proximity to an object) or a 3D data-point cloud. The AGV's controls receive a computer model derived from the data. This lets the forklift maneuver, load and unload pallets, verify remaining space within the truck, and track the number of remaining pallets.

AGV maker Transbotics, Charlotte, N.C., sponsored the software development and plans to use it in real manufacturing situations this year.


Voice your opinion!

To join the conversation, and become an exclusive member of Machine Design, create an account today!