Autonomous robots are one of the main pillars of IR 4.0, and there has been a high level of interest given that robots can do more on their own, including learning on the job and teaming up with other robots and humans.
In this backdrop of IR 4.0, computer scientists at the University of Leeds are using the artificial intelligence (AI) techniques of automated planning and reinforcement learning to "train" a robot to find an object in a cluttered space, such as a warehouse shelf or in a fridge - and move it.
The aim is to develop robotic autonomy, so the machine can assess the unique circumstances of the task and find a solution, similar to a robot transferring skills and knowledge to a new problem.
The big challenge is that in a confined area, a robotic arm may not be able to grasp an object from above. Instead it has to plan a sequence of moves to reach the target object, perhaps by manipulating other items out of the way. The computer power needed to plan such a task is so great, the robot will often pause for several minutes. And when it does execute the move, it will often fail.
The path to practice and perfectionTo solve this challenge, the computer scientists are bringing together two ideas from AI.
The first is 'automated planning', where the robot is able to "see" the problem through a vision system, in effect an image. This helps the robot's operating system simulate the possible sequence of moves it could make to reach the target object.
But the simulations that have been "rehearsed" by the robot fail to capture the complexity of the real world and when they are implemented, the robot fails to execute the task. For example, it can knock objects off the shelf.
So the team has combined planning with another AI technique called 'reinforcement learning'.
This involves the computer in a sequence of about 10,000 trial-and-error attempts to reach and move objects. Through these attempts, the robot "learns" which actions it has planned are more likely to end in success.
The computer undertakes the learning itself, starting off by randomly selecting a planned move that might work. But as the robot learns from trial-and-error, it becomes more adept at selecting those planned moves that have a greater chance of being successful.
Dr Matteo Leonetti, from the School of Computing, said: "AI is good at enabling robots to reason - for example, we have seen robots involved in games of chess with grandmasters.
"But robots aren't very good at what humans do very well: being highly mobile and dexterous. Those physical skills have been hardwired into the human brain, the result of evolution and the way we practice and practice and practice."
According to Wissam Bejjani, a PhD student who wrote the research paper, the robot develops an ability to generalise, to apply what it has planned to a unique set of circumstances.
He said: "With one problem, where the robot had to move a large apple, it first went to the left side of the apple to move away the clutter, before manipulating the apple. It did this without the clutter falling outside the boundary of the shelf."
Dr Mehmet Dogar, Associate Professor in the School of Computing, was also involved in the study. He said the approach had sped up the robot's "thinking" time by a factor of ten - decisions that took 50 seconds now take five seconds.