Pattern Formation Based on Potential Field in Real-Time Strategy Games

Real-time strategy (RTS) game is a very popular genre of computer games. In RTS games, the units need to navigate the environment, surround the enemy, and attack targets. Pattern formation of the units plays an important role in the tactics of RTS games. In this paper, we propose generating the pattern formation based on potential field, which is widely used in collision avoidance. The proposed method controls the movement of units and adjusts their formation considering the number and types of targets. More specifically, once a unit detects the target, it will move in accordance with other units to surround the targets in an attacking distance. The simulation results on Star Craft show the capability of the proposed method to generate pattern formation and adapt to the number and types of enemies.

[1]  Sushil J. Louis,et al.  Evolving coordinated spatial tactics for autonomous entities using influence maps , 2009, 2009 IEEE Symposium on Computational Intelligence and Games.

[2]  Yan Meng,et al.  Morphogenetic Robotics: An Emerging New Field in Developmental Robotics , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[3]  Stefan J. Johansson,et al.  The Rise of Potential Fields in Real Time Strategy Bots , 2008, AIIDE.

[4]  Oliver Kramer,et al.  Evolution of Human-Competitive Agents in Modern Computer Games , 2006, 2006 IEEE International Conference on Evolutionary Computation.

[5]  Ian Millington,et al.  Artificial Intelligence for Games , 2006, The Morgan Kaufmann series in interactive 3D technology.

[6]  Oussama Khatib,et al.  Real-Time Obstacle Avoidance for Manipulators and Mobile Robots , 1985, Autonomous Robot Vehicles.

[7]  Chih-Sheng Lin,et al.  Emergent Tactical Formation Using Genetic Algorithm in Real-Time Strategy Games , 2011, 2011 International Conference on Technologies and Applications of Artificial Intelligence.

[8]  Yan Meng,et al.  A Hierarchical Gene Regulatory Network for Adaptive Multirobot Pattern Formation , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).