Abstract
The collective perception problem is commonly discussed in swarm robotics, with many proposed solutions. However, there has been less discussion on the impact of faulty agents on the efficacy of these decision making strategies, and few possible solutions to mitigate any negative effects. This paper introduces a decentralised, immuno-inspired ‘check, track, mark’ (CTM) routine, and tests its efficacy when used to mitigate the effect of faulty agents in the collective perception problem. The CTM routine is inspired by macrophages in the human immune system, and their use in preventing pathogens from infecting healthy cells. We test the routine using three previously established decision making strategies, and a model of a detection algorithm with saturating true-positive and false-positive rates. We find that the proposed approach improves the ability of agents to reach an accurate consensus in the presence of faulty agents across all three of the decision making strategies tested, with increases in accuracy between 15–213%. For one strategy, the CTM routine also allows for an accurate consensus to be reached in fewer timesteps, with a median decrease in time to consensus of 29%. Out of the parameters associated with the CTM routine, we find the interval between initial checks to be most significant in affecting the speed and accuracy of the group in reaching consensus.