Homeostatic machines for Resilience and Adaptability

具有弹性和适应性的稳态机器

• 批准号: EP/X017486/1
• 负责人: Dana Damian
• 金额: $ 25.76万
• 依托单位: University of Sheffield
• 依托单位国家: 英国
• 项目类别: Research Grant
• 财政年份: 2023
• 资助国家: 英国
• 起止时间: 2023 至 无数据
• 项目状态: 未结题
• 来源: https://gtr.ukri.org/projects?ref=EP%2FX017486%2F1
• 关键词: Homeostatic; machines; Resilience; Adaptability

Nature offers a mechanism, called homeostasis, by which life forms can maintain their physical integrity and well being. On the other hand, series of machines, including robots, cannot overcome some of the most insignificant damage, such as a cut in a functional component. The aim of this project is to develop a fundamental physical homeostatic framework in order to endow machines with the ability to sustain themselves at high entropic states such as hazards and unpredictable conditions - that is, to autonomously prevent faults and restore internal parameters balance, and thus allow the machine's continuing operation. The project will provide the first fundamental building blocks of physical homeostasis toward machines with a new level of artificial intelligence (emotional AI) to enhance their resilience, adaptability and decision making in most uncertain tasks, and show empathic behavior in societal settings. The project will provides transformative tools for the science and engineering of intelligent systems: Responsible innovation, Emotional artificial intelligence, Trusted and emphatic technologies.

大自然提供了一种称为内稳态的机制，通过这种机制，生命形式可以保持其身体的完整性和健康。另一方面，包括机器人在内的一系列机器无法克服一些最微不足道的损坏，例如功能部件的切割。该项目的目的是开发一个基本的物理稳态框架，以便赋予机器在高熵状态下维持自身的能力，例如危险和不可预测的条件-也就是说，自主防止故障并恢复内部参数平衡，从而使机器能够继续运行。该项目将为具有新水平人工智能（情感AI）的机器提供物理稳态的第一个基本构建模块，以增强它们在大多数不确定任务中的弹性，适应性和决策能力，并在社会环境中表现出移情行为。该项目将为智能系统的科学和工程提供变革性工具：负责任的创新，情感人工智能，可信和创新技术。

项目成果

Data-Driven and Compliance-Based Fault-Tolerance for a Flexible and Extendable Robotic Implant Coupled to a Growing Tissue

• DOI: 10.1109/lra.2023.3243440
• 发表时间: 2023-04
• 期刊: IEEE Robotics and Automation Letters
• 影响因子: 5.2
• 作者: M. Pontin;Dana D. Damian