KAUST researchers have developed a new fault-detection system to keep robot swarms from malfunctioning and eroding overall performance.
Considered to be the fastest and most accurate fault-detection system to date, this invention could be a boon to industrialists using robot swarms in distribution warehouses.
“The philosophy behind swarm robotics is inspired by animal societies, such as ants and bees,” says KAUST researcher Fouzi Harrou, who along with Ying Sun developed the system.
“Groups of robots can cooperate to perform complex tasks that would be impossible with a single robot, which is very useful in many applications, such as cooperative search and exploration, managing warehouses, delivering products, seeding and harvesting.”
The software used to control the coordinated activity of robot swarms tries to account for the reality that assigned tasks are generally not always going to be executed at the desired performance level due to failures by one or more robots in the swarm.
Controlling a huge army of robots is anything but easy with external interference, unexpected collisions, component faults, software bugs and even broken communication links plaguing the machines.
It is thus crucial for operators to detect and identify possible faults or failures in the monitored robotic swarm system as early as possible to maximize operating efficiency and avoid expensive maintenance,” says Sun.
The researchers’ non-mathematical, fault-detection method starts by deriving performance metrics from relative-position data collected under normal operating conditions and then applies two standard ‘control chart’ methods as commonly used in industrial processes to rapidly test for any deviation from those metrics over time.
“We tested our improved data-based fault-detection strategy by applying it to a simulated swarm of foot-bot robots,” says Harrou. “For all the fault types tested – abrupt faults, drift faults, random walks and complete stop faults – our method resulted in a significant improvement in fault detection compared with existing approaches.”
Sun contends that the team is now planning to test their method on swarms of flying robots.
Image and content: Kittipong Jirasukhanont-Alamy Stock Photo/KAUST
