scholarly journals A Vector-agent Approach to (Spatiotemporal) Movement Modelling and Reasoning

Author(s):  
Saeed Rahimi ◽  
Antoni B. Moore ◽  
Peter A. Whigham

Abstract Modelling a complex system of autonomous individuals moving through space and time essentially entails understanding the (heterogeneous) spatiotemporal context, interactions with other individuals, their internal states and making any underlying causal interrelationships explicit, a task for which agents (including vector-agents) are specifically well-suited. Building on a conceptual model of agent space-time and reasoning behaviour, a design guideline for an implemented vector-agent model is presented in this article as an example. The movement of football players was chosen as it is appropriately constrained in possible space, time and individual actions. Sensitivity-variability analysis was applied to measure the performance of different configurations of system components on the emergent movement patterns. The model output varied more when the condition of the contextual actors (players’ role-areas) were manipulated. In conclusion, ABMs can contribute to our understanding of movement and how causally-relevant evidence could be produced, through a proposed agent equipped with active causal knowledge.

2004 ◽  
Vol 17 (5) ◽  
pp. 1069-1082 ◽  
Author(s):  
Dominique Tapsoba ◽  
Mario Haché ◽  
Luc Perreault ◽  
Bernard Bobée

2017 ◽  
Vol 21 ◽  
pp. 460-474 ◽  
Author(s):  
Yong Ge ◽  
Yue Yuan ◽  
Shan Hu ◽  
Zhoupeng Ren ◽  
Yijin Wu

Author(s):  
Nuno André Nunes ◽  
Bruno Gonçalves ◽  
Diogo Coutinho ◽  
Fábio Yuzo Nakamura ◽  
Bruno Travassos

The aim of this investigation was to analyse the external workload, tactical individual actions of passing, and perceived internal load during unbalanced small-sided games. Ball possession formats (4v3, 4v4 and 4v5) were played in three different playing area dimensions (20 × 15m, 25 × 20m and 30 × 25m) by under-23 football players. Data were analysed under opposition-based perspective, by fixing one team (4vX), and by cooperation-based perspective according to teammates (4v2+X) for each playing area condition. GPS monitors were used to collect and compute external workloads (distance covered while walking, running, sprinting, and maximal speed) and tactical individual actions (passing with dominant and non-dominant foot, and maximum passing speed), and Borg Scale CR10 to evaluate rating of perceived exertion (RPE). On both opposition- and cooperation-based perspectives, significant differences were found on external workload variables for all game formats, with smaller areas associated with more distances covered while walking and larger areas with running and sprinting. Likewise, 4v3, 4v4 and 4v2 + 3 revealed significant differences for tactical individual actions, where a larger area was associated with an increase in repetitions. Medium playing area, for both perspectives, was associated with a higher RPE. Overall, larger playing areas with higher number of players involved promoted more high-intensity running, while the same area with fewer number of players fostered tactical individual actions. Smaller areas allowed to reduce game pace, especially in formats with fewer players. Different unbalance scenarios under dissimilar playing area dimensions promote diverse performance outcomes on player’s action capabilities.


2021 ◽  
Vol 10 (2) ◽  
pp. 1-27
Author(s):  
Takafumi Sakamoto ◽  
Akihito Sudo ◽  
Yugo Takeuchi

We propose an agent model that determines its behavior from an internal state and a spatial relationship with a target to generate approaching and avoiding behaviors in encounter scenes. This model is based on the relationship with an opponent rather than with a scenario. The agent moves to increase the utility value obtained from the preferences for both aggressive and passive involvement. We analyzed the behavioral and utterance data of human–human interactions based only on two-dimensional position information by simple-shaped robots. The rate of participants’ behavior following the model was significantly higher than that of a random walker. Based on this result, we estimated the internal state during the interactions from the behavior of the participants and analyzed it. The words uttered by one member of a pair correlated with the internal state estimated from the behavior of the other member of the pair. The frequency of the internal states observed from the participants who were recommended to interact with the partner was different from that observed from the participants who did not receive such recommendations. These results suggest that a model with two preferences can approximate a human’s internal state in encounter scenes.


Author(s):  
P. Kefalas ◽  
M. Holcombe ◽  
G. Eleftherakis ◽  
M. Gheorghe

Recent advances in both the testing and verification of software based on formal specifications have reached a point where the ideas can be applied in a powerful way in the design of agent-based systems. The software engineering research has highlighted a number of important issues: the importance of the type of modelling technique used; the careful design of the model to enable powerful testing techniques to be used; the automated verification of the behavioural properties of the system; and the need to provide a mechanism for translating the formal models into executable software in a simple and transparent way. An agent is an encapsulated computer system that is situated in some environment and that is capable of flexible, autonomous action in that environment in order to meet its design objectives (Jennings, 2000). There are two fundamental concepts associated with any dynamic or reactive system (Holcombe & Ipate, 1998): the environment, which could be precisely or ill-specified or even completely unknown and the agent that will be responding to environmental changes by changing its basic parameters and possibly affecting the environment as well. Agents, as highly dynamic systems, are concerned with three essential factors: a set of appropriate environmental stimuli or inputs, a set of internal states of the agent, and a rule that relates the two above and determines what the agent state will change to if a particular input arrives while the agent is in a particular state. One of the challenges that emerges in intelligent agent engineering is to develop agent models and agent implementations that are “correct.” The criteria for “correctness” are (Ipate & Holcombe, 1998): the initial agent model should match the requirements, the agent model should satisfy any necessary properties in order to meet its design objectives, and the implementation should pass all tests constructed using a complete functional test-generation method. All the above criteria are closely related to stages of agent system development, i.e., modelling, validation, verification, and testing.


2002 ◽  
Author(s):  
J. B. Kennedy
Keyword(s):  

Sign in / Sign up

Export Citation Format

Share Document