University of South Australia (UniSA) engineers have developed a new algorithm to help robots avoid moving obstacles such as humans in their path.
In a new paper published in the Journal of Field Robotics, UniSA mechatronics engineering lecturer Dr Habib Habibullah describes how he and his team combined the best elements of existing algorithms to achieve a collision-free TurtleBot able to adjust its speed and steering angles.
Their computer model basically helps mobile robots recognize and avoid unexpected obstacles, finding the quickest and safest path to their destination.
“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,” notes Habibullah. “The first is fairly easily to program but the second is more challenging.”
There are already several algorithms on the market that have been tasked with addressing the issue of robots colliding with moving objects, but none of these are foolproof.
So in order to make their algorithm better, the UniSA team tested their model against two common online collision avoidance algorithms – Dynamic Window Approach (DWA) and Artificial Potential Field (APF).
Simulations in nine different scenarios were created and these were compared to collision rates, average time to destination, and the average speed of the robot.
In every scenario, the UniSA-designed algorithm helped robots successfully navigate a path without any collisions.
In comparison, the DWA model was only 66% effective, colliding with objects in three of the nine simulations.
The APF model fared better; it was also collision-free but took more time to reach its destination.
“Our proposed method sometimes took a longer path, but it was faster and safer, avoiding all collisions,” notes Habibullah.
According to the lecturer, the UniSA algorithm can be applied in many environments, including industrial warehouses where robots are commonly used, for robotic fruit picking, packing and pelletizing, and also for restaurant robots that deliver food from the kitchen to the table.
What distinguishes the UniSA-designed algorithm even further is that it can direct the TurtleBot to stop, take a turn and even reverse direction if it encounters anything in its path.
It could also be a potential solution for agricultural robots where children, pets and other animals are often present, opines Habibullah.
Image and content: matop_m in CircuitsRobots-Instructables/UniSA