THE HUMAN-ROBOT CLOUD: SITUATED COLLECTIVE INTELLIGENCE ON DEMAND Nikolaos Mavridis New York University AD PO Box 129188 Abu Dhabi, UAE nikolaos.mavridis@nyu.edu Thirimachos Bourlai West Virginia University PO Box 6109 Morgantown, WV 26506-6109 thirimachos.bourlai@mail.wvu.edu Dimitri Ognibene Imperial College Elec. And Electronic Eng. Dept London SW7 2BT d.ognibene@imperial.ac.uk Abstract—The Human-Robot Cloud (HRC) is an innovative extension of Cloud Computing across two important directions: First, while traditional cloud computing enables transparent utilization of distributed computational as well as storage resources, the HRC enables, in addition to the above two, the utilization of (a) distributed sensing (sensor network technology) and (b) actuator networks (including robot networks). Thus, HRC extends the concept of cloud computing by connecting it to the "Physical World", through sensing and action. Second, while traditional cloud computing involves the usage of only electronic components, such as computers and storage devices, the HRC's capability is extended by the support of human physical and cognitive “components” as part of the cloud, which are neither expected to be experts nor to be engaged with the cloud full-time. Such components are primarily expected to interact with the system for only short periods of time (seconds), essentially providing crowd-servicing for the Cloud. Human components provide any or a mixture of the following: a) input arising from a number of sources through the usage of their sensory faculties (auditory, visual etc.), - thus, acting as “intelligent sensors” attached to the cloud; b) input that results from the usage of their cognitive faculties (pattern recognition, prediction, identification, planning etc.) – thus, acting as “intelligent systems” attached to the cloud; and c) actuation services to the Cloud (by moving around their bodies or other objects) – thus acting as “actuators” attached to the cloud. Thus, the proposed HRC is aiming to achieve the best of both worlds, i.e., either humans or machines, being able to carry out tasks which are very difficult or impossible for either humans or machines alone to carry out. Furthermore, the HRC enables the construction of situated agents exhibiting collective intelligence on demand, and the transformation of situated agency from a “capital investment” to a service, components of which can be provided by multiple providers, in a transparent fashion to the end user Keywords-robots; cloud computing; human computation; sensor networks; crowd-sourcing; crowd-servicing I. INTRODUCTION Computation, software, data access, and storage services, traditionally require end-user knowledge of the physical location, as well as ownership and configuration of the system that delivers the services. Users or organizations, requiring computational power or storage space, have to physically buy and usually own (or long-term lease) physical computers and storage devices. However, despite its simplicity, the main disadvantages of such a traditional concept are the following: a) a large initial capital investment; b) large amounts of potentially unused computational power and/or storage space during the lifetime of the system; and c) the concept's limitation to peak computational throughput and storage space due to hardware constraints. Hence, the concept of cloud computing has recently been proposed that overcomes the aforementioned limitations. Numerous cloud computing-based services are already operational [1-4], and considerable related research has and is taking place [5-8]. With cloud computing, the delivery of computing takes the form of a service rather than a product. In addition, shared resources (computational and storage power) as well as software and information, are provided to the end-users as a utility (like the electricity grid) over a network. Thus, the shared resources are provided to the end-user, without the need for him/her to know where the machines provided are physically located, or what the specifics of the configuration of such machines are. In essence, cloud computing aims to achieve transparent sharing of distributed resources, which can be utilized by multiple users. Some of the main advantages of cloud over traditional computing are the following: First, for a large cloud, practically the peak computational throughput (that can be sustained for small periods of time) is high; and thus, bursts of activity can be accommodated. Second, depending on the Service-Level Agreement (SLA) between the user and the Ease of Use cloud, periods of zero or low activity can have little or no cost. Third, and quite importantly, there can usually be easy scalability to the cloud, as well as high robustness. As computational processes are not dispatched to faulty nodes, and replacement nodes are abundant, extra capacity can be added on demand, and reliability can be much higher. However, despite all of the above advantages, traditional cloud computing has one important limitation: it is not effectively connected to the physical world, in the way that a situated robotic agent would be. This is the case, as traditional cloud computing does not include components that directly sense the physical world (cameras, microphones, temperature and motion sensors etc.), nor does it include components that can directly act upon the physical world (motors, robotic arms, mobile robots, UAVs, etc.). We thus propose a two-fold extension of the traditional concept of cloud computing, that is expected to transform 978-1-4673-1419-0/12/$31.00 © 2012 IEEE 360 Proceedings of the 2012 IEEE International Conference on Cyber Technology in Automation, Control and Intelligent Systems May 27-31, 2012, Bangkok, Thailand