NSF-CONACyT: Ecological Robotics: A Schema-Theoretic Approach

NSF-CONACyT：生态机器人：图式理论方法

• 批准号: 9505864
• 负责人: Ronald Arkin
• 金额: $ 10.65万
• 依托单位: Georgia Tech Research Corporation
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 1995
• 资助国家: 美国
• 起止时间: 1995-08-01 至 1998-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=9505864&HistoricalAwards=false
• 关键词: NSF; CONACyT; Ecological; Robotics; Schema

This award, under the U.S.-Mexico CONACyT Initiative, is concerned with an in-depth scientific understanding of the nature of the relationship between mobile robotic agents and their environment. The research addresses the agent-environment relationship directly using schema theory and neurophysiological and ethological models to ultimately provide credible, generalizable, and useful results in this domain. These systems will ultimately be grounded in both simulations and actual robotic hardware. An in-depth understanding and dynamic modeling of the relationship a robot has with its environment (i.e., the overall ecology) is important to ensure that fielded robotic systems don't compete inappropriately with other agents that can do the task more effectively (and by competing, reduce their usefuless); that the robots are successful competitors within the ecological system and can potentially displace less efficient agents; and that they are ecologically sensitive so that agent-environmental system dynamics are well-modeled and as predictable as possible whenever new robotic technology is introduced. The research efforts will be tied together through the use of software tools already in existence or under development at both sites, including NSL, a neural simulation language; ASL, an abstract schema language; and MissionLab, a schema-based mission-oriented simulation and robot implementation environment.

这个奖项，根据美国-墨西哥国家科学技术委员会倡议，关注的是对移动的机器人代理人与其环境之间关系的性质的深入科学理解。 该研究直接使用图式理论和神经生理学和行为学模型来解决代理-环境关系，最终在这一领域提供可信的，可推广的和有用的结果。 这些系统最终将在模拟和实际机器人硬件中得到应用。 对机器人与其环境的关系的深入理解和动态建模（即，整体生态学）对于确保部署的机器人系统不会与能够更有效地完成任务的其他智能体进行不适当的竞争是重要的（通过竞争，减少它们的有用性）;机器人是生态系统中成功的竞争者，可以潜在地取代效率较低的代理人;并且它们在生态上是敏感的，因此每当引入新的机器人技术时，代理-环境系统动力学都是良好建模的并且尽可能可预测。 研究工作将通过使用两个站点已经存在或正在开发的软件工具结合在一起，包括NSL，神经模拟语言; ASL，抽象模式语言;和MissionLab，基于模式的面向任务的模拟和机器人实施环境。