Robots are currently able to communicate and coordinate in order to make decisions and carry out simple tasks. But could robots in the future carry out missions that require them to determine which tasks to perform and in what order to perform them?
For example, could robots soon save the survivors of a natural disaster? The ability to plan ahead in challenging times is a complex cognitive skill, and it typically emerges from the interactions between the individuals in a group. The researchers have based their study on swarm robotics, a branch of robotics that applies the organized behavior of social animals such as ants in order to produce groups of robots that exhibit artificial intelligence. In this study, they have developed a swarm of robots that can perform a sequence of three actions, without knowing the correct order in advance.
During the test, the robots were required to move to three different points in space, where they were to perform a simple task. Only after the tasks were completed would the robots learn whether the order was correct. To solve this problem, some of the robots gradually formed a chain between the three points in space, which the others used as a guide as they tested the various possible combinations by following instructions from the robots who made up the chain.
Eventually, they determined the correct sequence by working together. This study demonstrates, that robots are able to collectively determine a sequence of actions whose required order was previously unknown. This research paves the road to a number of future applications involving missions in which the ability to autonomously determine the order in which tasks should be completed are needed, such as searching for survivors after a natural disaster, exploring unknown or hostile environments, building structures on dangerous sites, and various applications in agriculture.