Discovering New Ways to Navigate: A Swarm Intelligence-Based Robotic Search Algorithm Integrated with Game Theory

Robotics has come a long way in the last few decades, and we continue to see innovations in the field as researchers seek to improve robotic search algorithms. Recently, researchers have proposed a decentralize and asynchronous swarm robotic search algorithm integrated with game theory to better disperse robots in the environment while crossing obstacles and solving mazes. This prevents early convergence and improves the efficiency of the searches.

In the proposed algorithm, individual robots, while searching, play a sequential game at each iteration, and based on that, choose their velocity update rule. This strategic game works well in search environments with different levels of complexity and especially improves search efficiency further in complex environments. In the target problem, since the environment is unknown, it is not possible to preplan a path to the target. And there is no difference between static and dynamic obstacles, as the robots cannot distinguish them. Thus, in the proposed method, passing and avoiding obstacles are synchronized with the target searching.

Example of a maze-like complex environment and its mapping to a fitness function

The simulation results showed that, following the proposed algorithm, robots disperse well in search environments, and therefore search speed increases by up to 24% and attended path length to target lessens by up to 23.5% in complex search environments. Also, the proposed algorithm has a success rate equal to the state-of-the-art, which is 100% in all of the tested environments.

For more details check out the paper:

Khalil Alrahman Youssefi Darmian, Modjtaba Rouhani, Habib Rajabi Mashhadi, and Wilfried Elmenreich. A swarm intelligence-based robotic search algorithm integrated with game theory. Applied Soft Computing, 122, 4 2022. (doi:10.1016/j.asoc.2022.108873)

Robotics is an exciting and ever-evolving field, and this new algorithm shows us the potential of swarm intelligence-based robotic search algorithms. We look forward to seeing more innovations in this area as researchers continue to explore new ways to navigate.