UniSA researchers create improved robot routing algorithm

Mobile robots are an increasingly important part of logistics processes, but they generally operate alongside humans.

Habibullah’s team combined the best elements of existing algorithms to deliver speed and safety.

“There are two types of path planning strategies for mobile robots, depending on whether they are being used in fixed environments or where they are encountering moving obstacles, such as humans or machines,” he said.

“The first is fairly easily to program but the second is more challenging.”

The researchers tested their model against two commonly used algorithms – Dynamic Window Approach (DWA) and Artificial Potential Field (APF) – and found theirs gave superior results.

The tests involved nine different scenarios, and the UniSA-designed algorithm helped robots successfully navigate a path without any collisions. The DWA model collided with objects in three of the nine scenarios, and while the APF model was collision-free, it took longer to reach its destination.

“Our proposed method sometimes took a longer path, but it was faster and safer, avoiding all collisions,” said Habibullah.

The improved algorithm could be applied in environments including industrial warehouses, fruit picking, packing and palletising, and even in restaurants that use robots that deliver food from the kitchen to the table.

“This could also be a potential solution for agricultural robots, for example autonomous lawn mowers, ground robots for crop surveillance and autonomous weeding robots, where children, pets and other animals are often present,” he said.

A paper describing the research has been published in the Journal of Field Robotics.

Image: Techwords via Wikimedia Commons, CC BY-SA 4.0