Modeling and Analysis of Soccer Robot Tasks Using Generalized Stochastic Petri Nets

Modeling and Analysis of Soccer Robot Tasks Using Generalized Stochastic Petri Nets
复制标题

DOI:
10.4028/www.scientific.net/ssp.166-167.133
复制
发表时间:
2010-09
期刊:
Solid State Phenomena
影响因子:
--
通讯作者:
D. Coman;N. Bîzdoaca;A. Petrisor;A. Ionescu;M. Florescu
D. Coman;N. Bîzdoaca;A. Petrisor;A. Ionescu;M. Florescu
中科院分区:
其他
文献类型:
--
作者:
D. Coman;N. Bîzdoaca;A. Petrisor;A. Ionescu;M. Florescu

文献摘要

被引文献

相似文献

机器人足球比赛为机器人技术的研究提供了极好的机会。特别是,足球机器人必须执行实时视觉识别,在动态领域中导航,避开障碍物,与队友合作,并将球踢向正确的方向。所有这些任务都要求机器人是自主的(感知,思考和作为独立的生物),高效的(在时间和资源限制下运作),合作的(与其他机器人合作完成超出个人能力的任务)和智能的(推理和规划行动,也许从经验中学习)。本文提出了一种用Petri网定义和分析攻击机器人任务的方法。利用广义随机Petri网对足球机器人的进攻行为进行建模。使用Petri网允许定性和定量分析的任务执行。在MATLAB环境下实现了Petri网建模。因此,它验证了网络拓扑结构,(它们的动态)的演变,结构和行为属性(对应于检查资源使用是否稳定,模型是否没有死锁),以及随机性能。
Robot soccer competition provides an excellent opportunity for robotics research. In particular, the soccer robots must perform real-time visual recognition, navigate in a dynamic field, avoid the obstacle, collaborate with teammates, and kick the ball in the correct direction. All these tasks demand robots that are autonomous (sensing, thinking, and acting as independent creatures), efficient (functioning under time and resource constraints), cooperative (collaborating with each other robot to accomplish tasks that are beyond individual’s capabilities), and intelligent (reasoning and planing actions and perhaps learning from experience). This paper proposes a method of defining and analysing the attacking robot tasks using Petri nets. Attacking soccer robot behaviors are modeled using the generalized stochastic Petri nets. Using Petri nets allows qualitative and quantitative analysis of the task execution. Petri net model is implemented in Petri Net Toolbox under MATLAB environment. Therefore, it is validated the net topology, the evolution of (their dynamics), the structural and behavioral properties (corresponding to checking if resources usage is stable and the model have no deadlocks), as well as the stochastic performance.