Towards a human-inspired control architecture for visually-guided action

面向视觉引导行动的人性化控制架构

• 批准号: EP/C533011/1
• 负责人: Dietmar Heinke
• 金额: $ 16.13万
• 依托单位: University of Birmingham
• 依托单位国家: 英国
• 项目类别: Research Grant
• 财政年份: 2006
• 资助国家: 英国
• 起止时间: 2006 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=EP%2FC533011%2F1
• 关键词: Towards; human; inspired; control; architecture

Despite the increasing sophistication of robotic systems, humans remain superior to robots in an impressive number of ways - not least when it comes to acting in natural environments. The proposed project aims at understanding a set of basic processes that are crucial for such interactions, with this understanding tested through the development of a computer model that is evaluated relative to human behaviour. The process to be modelled concern our ability to shape an action to a task-relevant object present in a complex (multi-object) environment. The proposed model is based on the premise that successful human actions depend on two forms of information: the abstract function of the objects (this is something to cut with) and the visual properties of the objects that are associated with action (that the handle but not the blade can be grasped). Psychological evidence also indicates that the intended action for a given task can influence how human attention is directed. Selection of the object to act upon is not separated from the selection of which action to make. To capture this, the selection of objects and the selection of actions will be modelled as interactive process.Prior work by the applicant provides a promising backdrop to the project. In particular, a model of object selection has been generated (the SAIM model) which has been successfully applied to a large body of psychological data. A second model has simulated how actions are select to single objects (the NAM model). In this project the models will be merged together, to simulate interactions between perceptual selection and action. The model will be realised using a neural-like architecture, and tested in comparison to human data. In the longer term, the model will provide an architecture for real-time control of a robot arm operating in a complex environment

尽管机器人系统的复杂性越来越高，但人类以令人印象深刻的方式仍然优于机器人 - 尤其是在自然环境中作用。拟议的项目旨在理解一组对于这种相互作用至关重要的基本过程，通过开发相对于人类行为进行评估的计算机模型，对这种理解进行了测试。要建模的过程涉及我们将动作塑造为复杂（多目标）环境中存在的与任务相关的对象的能力。所提出的模型基于以下前提：成功的人类行动取决于两种形式的信息：对象的抽象功能（这是要剪切的）以及与动作相关的对象的视觉属性（手柄但不是刀片可以抓住刀片）。心理证据还表明，给定任务的预期行动会影响人类注意力的指导方式。选择要采取的对象与选择哪种动作的选择并没有分开。为了捕获这一点，对象的选择和操作的选择将被建模为交互式过程。申请人提供的工作为项目提供了有希望的背景。特别是，已经生成了对象选择模型（SAIM模型），该模型已成功应用于大量的心理数据。第二个模型模拟了如何选择动作到单个对象（NAM模型）。在此项目中，模型将合并在一起，以模拟感知选择和动作之间的相互作用。该模型将使用类似神经的结构实现，并与人类数据进行了测试。从长远来看，该模型将为在复杂环境中运行的机器人组的实时控制提供架构

项目成果

Looking for intoolligence: A unified framework for the cognitive study of human tool use and technology.

寻找智能：人类工具使用和技术认知研究的统一框架。

• DOI: 10.1037/amp0000162
• 发表时间: 2018
• 期刊: The American psychologist
• 作者: Osiurak F

A novel diffusion-based model of choice reaching experiments

一种新颖的基于扩散的选择到达实验模型

• DOI: 10.1167/jov.20.11.776
• 发表时间: 2020
• 期刊: Journal of Vision
• 影响因子: 1.8
• 作者: Heinke D

Computational Modelling in Behavioural Neuroscience: Closing the gap between neurophysiology and behaviour

行为神经科学的计算模型：缩小神经生理学和行为之间的差距

• 发表时间: 2009
• 作者: D Heinke

Choice reaching with a LEGO arm robot (CoRLEGO): The motor system guides visual attention to movement-relevant information.

• DOI: 10.1016/j.neunet.2015.10.005
• 发表时间: 2015-12
• 期刊: Neural networks : the official journal of the International Neural Network Society
• 作者: Strauss S;Woodgate PJ;Sami SA;Heinke D
• 通讯作者: Heinke D

Modeling visual Affordances: The Selective Attention for Action Model (SAAM)

视觉可供性建模：行动选择性注意模型 (SAAM)

• 发表时间: 2009
• 作者: C Boehme