Autonomous task sequencing in a robot swarm

Can robots cooperate to solve together a complex cognitive problem that none of them can solve alone? A study recently published in Science Robotics shows that a swarm of robots can collectively determine the correct order in which some given tasks must be executed, even if the individual robots comprised in the swarm are unable to do it alone.

Swarm robotics is an approach to robotics inspired by the collective behaviors of social insects: in swarm robotics, a large number of robots are deployed to accomplish a mission that is beyond the capabilities of a single robot and requires that robots cooperate. Think, for example, of a group of robots that cooperate to drag an object that is too heavy for a single robot; or a group of robots that coordinate in order to position themselves so as to monitor a large environment and detect intrusion.

Robot swarms that can perform multiple tasks, one after the other, have already been demonstrated. However, these robot swarms have been developed under the hypothesis that the designer knows, at design time, the order in which tasks must be performed and/or the conditions under which robots must transition from task to task. This article advances the state of the art by demonstrating TS-Swarm: a robot swarm that autonomously sequences tasks at run time and can therefore operate even if the correct order of execution is unknown at design time.

The ability to sequence tasks endows robot swarms with unprecedented autonomy and is an important step towards the uptake of swarm robotics in a range of practical applications. Think for example of searching for survivors after a natural disaster, exploring unknown or hostile environments, or building structures in dangerous sites.

The research was conducted at IRIDIA, the artificial intelligence laboratory of the Université libre de Bruxelles, in the context of the project "DEMIURGE: automatic design of robot swarms," funded by the European Research Council through an ERC Consolidator Grant awarded to Mauro Birattari.