Path Planning, Reciprocal Altruism, Particle Swarm Optimization, PSO, RAPSO, Kinship. 

Encountering the problems of nature that has always been a challenging task, what makes it more difficult is the change in operating conditions over time. Therefore, a robust algorithm is needed that is able to track the continuously changing optima over time. In this thesis, a novel particle swarm optimization based population kinship connectivity is proposed with the intent to improve the performance by introducing the sharing of particles information. The proposed algorithm, Reciprocal Altruism based Particle Swarm Optimization, utilizes the kinship relatedness between particles during the optimization process to reciprocate the significant data regarding the environment.

Reciprocal altruism theory is regularly conjured to clarify why irrelative particles helped as pairs in different types of intra-group cooperative conduct, e.g., egg exchanging among hermaphroditic fishes, blood spewing forth among vampire bats, assessment of predator among sticklebacks, allogrooming among vervet monkeys and impala, sustenance share among humans, brown capuchin monkeys, and basic chimpanzees.

Utilizing the concept of reciprocation, the RAPSO will ensure that all particles remain in close contact with each other through information exchange. Moreover, the amount of information that is exchanged between the particles is dependent upon their physical placement in the search space regions. Depending upon their region, they can be either classified as a donor or a recipient; furthermore, the amount of information exchanged between the particles is directly monitored through their associated health indicator.  The performance of the proposed approach shows that the reciprocal sharing has played its role effectively in order to control the movement of the swarm along the optimized path. The simulation results proved that RAPSO outperforms the conical PSO algorithm both in terms of error reduction and close connectivity.