[论文解读] CLIC: A Framework for Distributed, On-Demand, Human-Machine Cognitive Systems

Nikolaos Mavridis, Stasinos Konstantopoulos+7 more|arXiv (Cornell University)|Dec 8, 2013

Personal Information Management and User Behavior参考文献 52被引用 4

一句话总结

CLIC 提出了一种分布式、按需的认知系统框架，整合了人类与机器组件，以克服传统人工智能系统中的局限性，实现动态、可重用、自修复及基于效用的运行。它支持实时、远程的人类输入，同时结合机器服务，使系统能够根据可用性、成本和需求即时组装与重构。

ABSTRACT

Traditional Artificial Cognitive Systems (for example, intelligent robots) share a number of limitations. First, they are usually made up only of machine components; humans are only playing the role of user or supervisor. And yet, there are tasks in which the current state of the art of AI has much worse performance or is more expensive than humans: thus, it would be highly beneficial to have a systematic way of creating systems with both human and machine components, possibly with remote non-expert humans providing short-duration real-time services. Second, their components are often dedicated to only one system, and underutilized for a big part of their lifetime. Third, there is no inherent support for robust operation, and if a new better component becomes available, one cannot easily replace the old component. Fourth, they are viewed as a resource to be developed and owned, not as a utility. Thus, we are presenting CLIC: a framework for constructing cognitive systems that overcome the above limitations. The architecture of CLIC provides specific mechanisms for creating and operating cognitive systems that fulfill a set of desiderata: First, that are distributed yet situated, interacting with the physical world though sensing and actuation services, and that are also combining human as well as machine services. Second, that are made up of components that are time-shared and re-usable. Third, that provide increased robustness through self-repair. Fourth, that are constructed and reconstructed on the fly, with components that dynamically enter and exit the system during operation, on the basis of availability, pricing, and need. Importantly, fifth, the cognitive systems created and operated by CLIC do not need to be owned and can be provided on demand, as a utility; thus transforming human-machine situated intelligence to a service, and opening up many interesting opportunities.

研究动机与目标

• 解决传统人工智能系统仅依赖机器组件、在关键任务中缺乏人类参与的局限性。
• 通过实现跨多个认知系统的时分共享与可重用性，克服系统组件的低效利用问题。
• 通过动态替换故障组件的自修复机制，提升系统鲁棒性。
• 通过允许组件在运行时根据可用性和价格动态加入或退出，实现系统运行时的即时构建与重构。
• 将人机认知系统从拥有资源转变为按需使用的效用模式，降低拥有门槛，提升可及性。

提出的方法

• 设计一种分布式架构，通过标准化接口整合人类与机器服务。
• 实现基于组件的系统，使服务在运行时实现时分共享与动态组合。
• 引入基于可用性、性能和成本指标的组件发现与选择机制。
• 通过监控组件健康状态，自动替换故障或性能不佳的组件，嵌入自修复能力。
• 采用面向服务的模型，实现认知系统作为效用的按需提供，将部署与拥有权解耦。
• 通过由框架编排的传感与执行服务，支持与物理世界的场景化交互。

实验结果

研究问题

• RQ1 如何构建认知系统，实现实时动态整合人类与机器组件？
• RQ2 哪些架构机制能够支持分布式认知系统中稳健的自修复运行？
• RQ3 如何在无需预先承诺的情况下，实现跨多个系统的组件重用与按需组合？
• RQ4 在认知系统中，如何有效整合人类贡献作为短时、远程的服务？
• RQ5 如何将认知系统转变为效用化模式，实现与拥有权的解耦并按需运行？

主要发现

• CLIC 支持以动态、按需的方式组合人类与机器组件，显著提升了系统的适应性与效率。
• 该框架可根据可用性、定价与性能实时重构系统组件，确保运行时的最优组合。
• 自修复机制可自动检测并替换故障组件，显著增强系统的长期鲁棒性。
• 通过时间共享实现组件重用，降低资源闲置利用率，提升系统效率。
• 效用化模型使认知系统可按需提供，无需拥有，从而降低部署门槛。
• 该架构成功实现系统构建与拥有权的解耦，支持人机认知系统的可扩展与灵活部署。