Employee robots have learned to detect and neutralize traitor robots

Researchers at the University of Lausanne developed an algorithm , which allows employee robots to identify and isolate rogue robots that may be disrupting the coherence and efficiency of the entire swarm. The algorithm is based on the majority vote principle and uses local information about the behavior of neighboring robots.

Employee robots are groups of autonomous robots that can perform various tasks in a collaborative manner, such as exploration, search and rescue, or construction. However, such robots are also subject to possible glitches, bugs, or malicious interference, which may cause some robots to act against the interests of the entire swarm. Such robots are called Byzantine robots.

Byzantine robots can create problems for the swarm, as they can communicate false or conflicting information to other robots, or act against the rules. For example, a Byzantine robot may point in the wrong direction, or refuse to follow the leader. This can lead to loss of synchronization, disunity, or even destruction of the swarm.

In order to prevent such situations, the researchers proposed algorithm, which allows employee robots to identify and isolate Byzantine robots. The blockchain-based algorithm works like this: each robot observes the behavior of its neighbors and compares it with the expected one. If the neighbor’s behavior deviates from the expected by a certain threshold, then the robot considers him suspicious and votes for his isolation. If the majority of robots in the neighborhood vote to isolate a suspicious robot, then it is disconnected from communication and interaction with the rest.

The researchers conducted experiments with real and virtual robots and showed that the algorithm is able to successfully detect and neutralize Byzantine robots in different scenarios. They also proved that the algorithm is resistant to measurement and communication errors, as well as random changes in the behavior of normal robots.