Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Ambient Intelligence: An Overview

Ambient Intelligence: An Overview

Short seminar about "Ambient Intelligence" for the Artificial Intelligence course at Politecnico di Torino (academic year 2014/2015)

Luigi De Russis

May 26, 2015
Tweet

More Decks by Luigi De Russis

Other Decks in Technology

Transcript

  1. THIS IS NOT AMBIENT INTELLIGENCE * this is a first

    step in the "right" direction, only
  2. sensitive intelligent ubiquitous transparent Able to sense the environments and

    its inhabitants. Able to process sensor data. responsive adaptive
  3. sensitive intelligent ubiquitous transparent Able to infer a situational context:

    - from environment data - from user data (identity, presence, actions, …) - from statistics and preferences - from external information sources Able to adapt to the context, by means of the interpretation of sensing and the generated response responsive adaptive
  4. sensitive intelligent ubiquitous "The most profound technologies are those that

    disappear. They weave themselves into the fabric of everyday life until they are indistinguishable from it." Mark Weiser transparent responsive adaptive
  5. sensitive intelligent ubiquitous Present, appearing, found everywhere. Able to be

    distributed over the ambient and over different people. transparent responsive adaptive
  6. sensitive intelligent ubiquitous Incorporates Artificial Intelligence: - Machine learning, agent-

    based software, robotics - Hearing, vision, language, knowledge processing - Semantic web, reasoning transparent responsive adaptive
  7. MAIN STEPS TOWARD A SUCCESSFUL AMI SYSTEM Sensing Acting Reasoning

    Interacting Needed to provide responsiveness and adaptability. Model, interpret and recognize context, users and their activities. Make decisions, e.g., acting vs. suggesting.
  8. HOW FAR ARE WE? THE RESEARCH WORLD IN 2015 sensitive

    intelligent responsive adaptive ubiquitous transparent Sensing Acting Reasoning Interacting
  9. AIR LAB Ambient Intelligence Research Lab Energy-Efficient User-centric Light Control

    in Smart Homes This project is based on the use of cameras and a distributed processing method for automated control of lights in a smart home. The implemented optimization formulations maintain the user's comfort while reducing the energy cost of lights. Information from camera sensors provides occupancy reasoning and human activity analysis. By employing the user's positions, activities, and preference as constraints, the system optimizes the light setting for the user's satisfaction in the occupied area. Reinforcement Learning for Ambient Intelligent Atmospheric Lighting and Music The goal is to create a user-centric methodology for adaptation of system services based on accumulated knowledge about the user preferences. These preferences are learned through user's explicit or implicit feedback to the system when the user opts to react to the provided service. As a result, the system adapts to provide the most satisfactory background music and ambient lighting to the user. In our approach, the system gains intelligence through observing the user, interacting with the user, and exploring the user's interests via mutual discovery mechanisms. Context is inferred not just through generic data such as time of the day, but also via detecting user- specific situation such as location, activity, or event. http://airlab.stanford.edu
  10. CHANGING PLACES MIT Media Lab CityHome The CityHome Lab is

    a 200 square-foot Living Laboratory designed to develop, deploy, test, and evaluate strategies for "living large in a small space", with a focus on the mechatronics of hyper-efficient transformable infill, new home interfaces, and technologies related to distributed work, proactive health, energy conservation, entertainment, and communication. The integration of these new systems and technologies creates urban dwellings that function as if they were much larger, minimize resource consumption, and develop rich living experiences for their occupants. http://cp.media.mit.edu https://www.youtube.com/watch?v=f8giE7i7CAE
  11. FLUID INTERFACES MIT Media Lab Reality Editor The Reality Editor

    is a system that supports editing the behavior and interfaces of so-called "smarter objects", i.e. objects or devices that have an embedded processor and communication capability. Using augmented reality techniques, the Reality Editor maps graphical elements directly on top of the tangible interfaces found on physical objects, such as push buttons or knobs. The Reality Editor allows flexible reprogramming of the interfaces and behavior of the objects as well as defining relationships between smarter objects in order to easily create new functionalities. Video: https://vimeo.com/74073989 http://fluid.media.mit.edu AutoEmotive Regardless of the emotional state of drivers, current cars feel impassive and disconnected. We believe that by adding emotion-sensing technologies inside the car, we can dramatically improve the driving experience while increasing the safety of drivers. This work explores the landscape of possible applications when incorporating stress-sensing devices in the car. Video: https://vimeo.com/85856989
  12. INTELLIGENT ENVIRONMENTS GROUP http://ieg.essex.ac.uk/ RESPONSIVE ENVIRONMENTS MIT Media Lab http://resenv.media.mit.edu

    CASAS Center for Advanced Studies in Adaptive Systems http://casas.wsu.edu/ GOODIES Research GrOup On Development of Intelligent EnvironmentS http://ie.cs.mdx.ac.uk/
  13. E-LITE Intelligent and Interactive Systems Ambient Intelligence Course Third year,

    elective course, for all the Engineering degree. In English. The course aims at describing, from an experimental point of view, the field of Ambient Intelligence, outlining its multi-disciplinary nature as well as its technology and application areas. Special emphasis, on the course, will be devoted to design-related aspects and on the overall hardware-software architecture, besides reviewing the involved technologies. This will enable students to design and realize reusable and interoperable solutions, and to collaboratively build a working prototype of an AmI system, in the laboratory. Projects website: http://ami-2015.github.io/, about a "Smart Politecnico" 2014 projects: http://ami-2014.github.io/ http://elite.polito.it
  14. E-LITE Intelligent and Interactive Systems Ambient Intelligence Course Third year,

    elective course, for all the Engineering degree. In English. The course aims at describing, from an experimental point of view, the field of Ambient Intelligence, outlining its multi-disciplinary nature as well as its technology and application areas. Special emphasis, on the course, will be devoted to design-related aspects and on the overall hardware-software architecture, besides reviewing the involved technologies. This will enable students to design and realize reusable and interoperable solutions, and to collaboratively build a working prototype of an AmI system, in the laboratory. Projects website: http://ami-2015.github.io/, about a "Smart Politecnico" 2014 projects: http://ami-2014.github.io/ http://elite.polito.it Public showcase of students' projects to be held on September 29, 2015 (in the evening) at I3P You are kindly invited!
  15. E-LITE Intelligent and Interactive Systems http://elite.polito.it HomeRules A considerable amount

    of research has been carried out towards enabling average users to customize their smart homes through trigger-action ("if... then...") programming. However, inhabitants of such smart environments keep having problems understanding, administering, troubleshooting, and deriving benefits from the technologies employed in their homes. HomeRules is a mobile and tangible application for end-user programming in smart homes. Video: https://www.youtube.com/watch?v=hswwY8j3yoI
  16. E-LITE Intelligent and Interactive Systems http://elite.polito.it HomeRules A considerable amount

    of research has been carried out towards enabling average users to customize their smart homes through trigger-action ("if... then...") programming. However, inhabitants of such smart environments keep having problems understanding, administering, troubleshooting, and deriving benefits from the technologies employed in their homes. HomeRules is a mobile and tangible application for end-user programming in smart homes. Video: https://www.youtube.com/watch?v=hswwY8j3yoI Thesis available on this topic
  17. E-LITE Intelligent and Interactive Systems http://elite.polito.it Smarter Notifications In the

    Internet of Things (IoT) world, we are under a constant stream of messages, coming from various "smart objects" (e.g., thermostats, washing machines, weather stations, activity trackers, drink trackers) and from different services and Social Network (like Facebook, Twitter, WhatsApp, e-mail, etc.). All these notifications may be interesting by themselves, but taken together they risk to be a constant distraction and annoyance. Moreover, they are "raw data", typically, from which we cannot immediately derive any suggestion or pattern for personal improvements or for a better understanding of some aspects of our life. Things become further complicated by the presence of "smart objects" that are shared between groups of people or family members (like a TV or a washing machine). Thus, data coming from such devices/appliances can affect multiple persons and their behaviors. We are working on a Smart Notification system, able to deliver the "right" notification, to the "right" person (or people), in the "right" moment, according to users' preferences, activities and to the notification characteristics.
  18. E-LITE Intelligent and Interactive Systems http://elite.polito.it Smarter Notifications In the

    Internet of Things (IoT) world, we are under a constant stream of messages, coming from various "smart objects" (e.g., thermostats, washing machines, weather stations, activity trackers, drink trackers) and from different services and Social Network (like Facebook, Twitter, WhatsApp, e-mail, etc.). All these notifications may be interesting by themselves, but taken together they risk to be a constant distraction and annoyance. Moreover, they are "raw data", typically, from which we cannot immediately derive any suggestion or pattern for personal improvements or for a better understanding of some aspects of our life. Things become further complicated by the presence of "smart objects" that are shared between groups of people or family members (like a TV or a washing machine). Thus, data coming from such devices/appliances can affect multiple persons and their behaviors. We are working on a Smart Notification system, able to deliver the "right" notification, to the "right" person (or people), in the "right" moment, according to users' preferences, activities and to the notification characteristics. Thesis available on this topic
  19. This work is licensed under the Creative Commons “Attribution- NonCommercial-ShareAlike

    Unported (CC BY-NC-SA 3,0)” License. You are free: – to Share - to copy, distribute and transmit the work – to Remix - to adapt the work Under the following conditions: – Attribution - You must attribute the work in the manner specified by the author or licensor (but not in any way that suggests that they endorse you or your use of the work). – Noncommercial - You may not use this work for commercial purposes. – Share Alike - If you alter, transform, or build upon this work, you may distribute the resulting work only under the same or similar license to this one. To view a copy of this license, visit http://creativecommons.org/license/by-nc-sa/3.0/ LICENSE