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

Mathematics ◽  
2022 ◽  
Vol 10 (1) ◽  
pp. 164
Author(s):  
Yan Li ◽  
Mengyu Zhao ◽  
Huazhi Zhang ◽  
Yuanyuan Qu ◽  
Suyu Wang

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.

2011 ◽  
Vol 317-319 ◽  
pp. 890-896
Author(s):  
Ming Jun Zhang ◽  
Yuan Yuan Wan ◽  
Zhen Zhong Chu

The traditional centroid tracking method over-relies on the accuracy of segment, which easily lead to loss of underwater moving target. This paper presents an object tracking method based on circular contour extraction, combining region feature and contour feature. Through the correction to circle features, the problem of multiple solutions causing by Hough transform circle detection is avoided. A new motion prediction model is constructed to make up the deficiency that three-order motion prediction model has disadvantage of high dimension and large calculation. The predicted position of object centroid is updated and corrected by circle contour, forming prediction-measurement-updating closed-loop target tracking system. To reduce system processing time, on the premise of the tracking accuracy, a dynamic detection method based on target state prediction model is proposed. The results of contour extraction and underwater moving target experiments demonstrate the effectiveness of the proposed method.


2018 ◽  
Vol 62 (1) ◽  
Author(s):  
Yingrong Yu ◽  
Siting Peng ◽  
Xiwang Dong ◽  
Qingdong Li ◽  
Zhang Ren

2020 ◽  
Vol 34 (05) ◽  
pp. 7253-7260 ◽  
Author(s):  
Yuhang Song ◽  
Andrzej Wojcicki ◽  
Thomas Lukasiewicz ◽  
Jianyi Wang ◽  
Abi Aryan ◽  
...  

Learning agents that are not only capable of taking tests, but also innovating is becoming a hot topic in AI. One of the most promising paths towards this vision is multi-agent learning, where agents act as the environment for each other, and improving each agent means proposing new problems for others. However, existing evaluation platforms are either not compatible with multi-agent settings, or limited to a specific game. That is, there is not yet a general evaluation platform for research on multi-agent intelligence. To this end, we introduce Arena, a general evaluation platform for multi-agent intelligence with 35 games of diverse logics and representations. Furthermore, multi-agent intelligence is still at the stage where many problems remain unexplored. Therefore, we provide a building toolkit for researchers to easily invent and build novel multi-agent problems from the provided game set based on a GUI-configurable social tree and five basic multi-agent reward schemes. Finally, we provide Python implementations of five state-of-the-art deep multi-agent reinforcement learning baselines. Along with the baseline implementations, we release a set of 100 best agents/teams that we can train with different training schemes for each game, as the base for evaluating agents with population performance. As such, the research community can perform comparisons under a stable and uniform standard. All the implementations and accompanied tutorials have been open-sourced for the community at https://sites.google.com/view/arena-unity/.


2019 ◽  
Vol 374 (1771) ◽  
pp. 20180030 ◽  
Author(s):  
Yukie Nagai

What is a fundamental ability for cognitive development? Although many researchers have been addressing this question, no shared understanding has been acquired yet. We propose that predictive learning of sensorimotor signals plays a key role in early cognitive development. The human brain is known to represent sensorimotor signals in a predictive manner, i.e. it attempts to minimize prediction error between incoming sensory signals and top–down prediction. We extend this view and suggest that two mechanisms for minimizing prediction error lead to the development of cognitive abilities during early infancy. The first mechanism is to update an immature predictor. The predictor must be trained through sensorimotor experiences because it does not inherently have prediction ability. The second mechanism is to execute an action anticipated by the predictor. Interacting with other individuals often increases prediction error, which can be minimized by executing one's own action corresponding to others’ action. Our experiments using robotic systems replicated developmental dynamics observed in infants. The capabilities of self–other cognition and goal-directed action were acquired based on the first mechanism, whereas imitation and prosocial behaviours emerged based on the second mechanism. Our theory further provides a potential mechanism for autism spectrum condition. Atypical tolerance for prediction error is hypothesized to be a cause of perceptual and social difficulties. This article is part of the theme issue ‘From social brains to social robots: applying neurocognitive insights to human–robot interaction’.


2013 ◽  
Vol 765-767 ◽  
pp. 1529-1532
Author(s):  
Zhao Dan Wu ◽  
Chang Feng Shi ◽  
Yi Lu

The intelligent information retrieval model discussed in this paper is constructed by multi-agent. Currently, BDI cognitive theory is accepted widely by the scholars of this field, but the related researches mainly focus on the theoretical derivation and presentation of symbols, lack of model facing practical application. In this article, a dynamic rule-based reasoning model is proposed. The model based on BDI theory is an expression of agent intelligence. The basic logical reasoning of the BDI theory is extended in this article. The author not only introduces several functions to study the dynamic changes of agents mental state, but also give a detailed description of how to use the theory of production rules to express BDI-based reasoning. This article also studies and designs the agent communication mechanism in MAS. Finally, the intelligent information retrieval system is designed and implemented with the idea of AOP.


2020 ◽  
Author(s):  
Tasiransurini Ab Rahman ◽  
Nor Azlina Ab. Aziz ◽  
Zuwairie Ibrahim ◽  
Nor Hidayati Abdul Aziz ◽  
Mohd Ibrahim Shapiai ◽  
...  

Abstract This paper investigates the potential of the ultimate iterative unbiased finite impulse response (UFIR) filter as a source of inspiration in a population-based metaheuristic algorithm. Here, a new algorithm inspired by the measurement and estimation procedures of the UFIR filter named the Multi-Agent Finite Impulse Response Optimizer (MAFIRO) for solving numerical optimization problems is proposed. MAFIRO works with a set of agents where each performs the measurement and estimation to find a solution. MAFIRO employs a random mutation of the best-so-far solution and the shrinking local neighborhood method to balance between the exploration and exploitation phases during the optimization process. Subsequently, the performance of MAFIRO is tested by solving the benchmark test suite of the IEEE Congress on Evolutionary Computation 2014. The benchmark is composed of 30 mathematical functions. The competency of MAFIRO is compared with the Particle Swarm Optimization algorithm, Genetic Algorithm, and Grey Wolf Optimizer. The results show that MAFIRO leads in 23 out of 30 functions and has the highest Friedman rank. MAFIRO performs significantly better than the other tested algorithms. Based on the findings, we show that the concept of the UFIR filter is a good inspiration for a population-based metaheuristic algorithm.


2004 ◽  
Vol 1268 ◽  
pp. 1261
Author(s):  
Kensaku Mori ◽  
Tsutomu Enjoji ◽  
Daisuke Deguchi ◽  
Takayuki Kitasaka ◽  
Yasuhito Suenaga ◽  
...  

2015 ◽  
pp. 234-246
Author(s):  
Anna Sugak ◽  
Oleksandr Martynyuk ◽  
Oleksandr Drozd

Operation testing and diagnostic tests, applied for distributed information systems, inherit and employ the properties of distribution, autonomy, goal formation and cooperation, natural for the multi-agent systems. This paper presents the behavioral diagnostics agent model, based on the evolutionary organization of component tests in the automata network environment. The model can be used to construct a multi-agent diagnostics system. A hybrid agent model provides a combination of reactive operation testing and deliberative diagnostic tests, based on the deterministic and evolutionary methods of synthesis of behavioral tests. An agent model consists of the component models of allocation environment, functioning goals and strategies, operations of observation, enforcement strategy and adaptation, initial component models, goals and strategies for ensuring the autonomy. Agent intelligence is based on a locally-exhaustive deterministic and pseudorandom targeted evolutionary synthesis of behavioral tests, providing and accumulating the results. Cooperation of the agents involves their deterministic and evolutionary interactions under the conditions of test feasibility and portability.


Electronics ◽  
2021 ◽  
Vol 10 (23) ◽  
pp. 2977
Author(s):  
Yan Li ◽  
Mengyu Zhao ◽  
Huazhi Zhang ◽  
Fuling Yang ◽  
Suyu Wang

Most current studies on multi-agent evolution based on deep learning take a cooperative equilibrium strategy, while interactive self-learning is not always considered. An interactive self-learning game and evolution method based on non-cooperative equilibrium (ISGE-NCE) is proposed to take the benefits of both game theory and interactive learning for multi-agent confrontation evolution. A generative adversarial network (GAN) is designed combining with multi-agent interactive self-learning, and the non-cooperative equilibrium strategy is well adopted within the framework of interactive self-learning, aiming for high evolution efficiency and interest. For assessment, three typical multi-agent confrontation experiments are designed and conducted. The results show that, first, in terms of training speed, the ISGE-NCE produces a training convergence rate of at least 46.3% higher than that of the method without considering interactive self-learning. Second, the evolution rate of the interference and detection agents reaches 60% and 80%, respectively, after training by using our method. In the three different experiment scenarios, compared with the DDPG, our ISGE-NCE method improves the multi-agent evolution effectiveness by 43.4%, 50%, and 20%, respectively, with low training costs. The performances demonstrate the significant superiority of our ISGE-NCE method in swarm intelligence.


Sign in / Sign up

Export Citation Format

Share Document