Using vision and coordination to find unknown target

This paper introduces a Vision based Learning real-time A* (VLRTA*) search algorithm where target position is unknown and unpredictable by agents in partially unknown/dynamic environment. We have mapped human vision for agents, which is omni directional vision but in a single direction at some point in time. Agents can not see through obstacles so vision can be blocked due to hurdles in search space. The proposed algorithm has been applied to solve randomly generated mazes with multiple agents. We have evaluated this algorithm on a large number of test cases with random obstacles and varying obstacle ratio. Through Experimental evaluations, we have shown that our suggested vision technique is effective in both locate target time and solution quality. Moreover, the strategy used in Vision Based LRTA* becomes more efficient if the number of agents is increased with proportion to obstacle ratio.