A Multi-Agent Motion Prediction and Tracking Method Based on Non-Cooperative Equilibrium

Abstract

A Multi-Agent Motion Prediction and Tracking method based on non-cooperative equilibrium (MPT-NCE) is proposed according to the fact that some multi-agent intelligent evolution methods, like the MADDPG, lack adaptability facing unfamiliar environments, and are unable to achieve multi-agent motion prediction and tracking, although they own advantages in multi-agent intelligence. Featured by a performance discrimination module using the time difference function together with a random mutation module applying predictive learning, the MPT-NCE is capable of improving the prediction and tracking ability of the agents in the intelligent game confrontation. Two groups of multi-agent prediction and tracking experiments are conducted and the results show that compared with the MADDPG method, in the aspect of prediction ability, the MPT-NCE achieves a prediction rate at more than 90%, which is 23.52% higher and increases the whole evolution efficiency by 16.89%; in the aspect of tracking ability, the MPT-NCE promotes the convergent speed by 11.76% while facilitating the target tracking by 25.85%. The proposed MPT-NCE method shows impressive environmental adaptability and prediction and tracking ability.

A Multi-Agent Adaptive Co-Evolution Method in Dynamic Environments

“…Co-evolution is used to realize collaboration between multi-agent [1] dealing with complex task environments. At present, most of the multi-agent co-evolution methods are based on stable and static environments with which the agents therein interact so that to generate experiences and learn to adapt to the environment gradually, such as the ISGE-NCE method and MPT-NCE method based on non-cooperative equilibrium [2,3]. However, in a dynamic environment where the task conditions are constantly changing, the best policy made by the agents based on the current information would no longer be the 'best' as the environment changes [4].…”