Intelligent Environments n n n Environments that use

Intelligent Environments n n n Environments that use technology to assist inhabitants by automating task components Aimed at improving inhabitants’ experience and task performance NOT: large number of electronic gadgets

Objectives of Intelligent Environments n Improve Inhabitant experience: n n n Optimize inhabitant productivity Minimize operating costs Improve comfort Simplify use of technologies Ensure security Enhance accessibility

Requirements for Intelligent Environments n n n Acquire and apply knowledge about tasks that occur in the environment Automate task components that improve efficiency of inhabitant tasks Provide unobtrusive human-machine interfaces Adapt to changes in the environment and of the inhabitants Ensure privacy of the inhabitants

Examples of Intelligent Environments n Intelligent Workspaces n Automatic note taking n Simplified information sharing n Optimized climate controls n Automated supply ordering

Examples of Intelligent Environments n Intelligent Vehicles n Location-aware navigation systems n Task-specific navigation n Traffic-awareness

Examples of Intelligent Environments n Smart Homes n n Optimized climate and light controls Item tracking and automated ordering for food and general use items Automated alarm schedules to match inhabitants’ preferences Control of media systems

Existing Projects n Academic n n n Georgia Tech Aware Home MIT Intelligent Room Stanford Interactive Workspaces UC Boulder Adaptive House UTA Mav. Home Smart Home TCU Smart Home

Existing Projects n Industry n General Electric Smart Home n Microsoft Easy Living n Philips Vision of the Future n Verizon Connected Family

Georgia Tech Aware Home n n n Perceive and assist occupants Aging in Place (crisis support) Ubiquitous sensing n n n Scene understanding, object recognition Multi-camera, multi-person tracking Context-based activity Smart floor http: //www. cc. gatech. edu/fce/ahri/

MIT Intelligent Room n n Support natural interaction with room n Speech-based information access n Gesture recognition n Movement tracking n Context-aware automation http: //www. ai. mit. edu/projects/aire/

Stanford Interactive Workspaces n n n Large wall and tabletop interactive displays Scientific visualization Mobile computing devices Computer-supported cooperative work Distributed system architectures http: //iwork. stanford. edu/

UC Boulder Adaptive House n Infer patterns and predict actions Machine learning for automation HVAC, water heater, lighting control Goals: n Reduce occupant manual control n Improve energy efficiency http: //www. cs. colorado. edu/~mozer/house/ n n

UTA Mav. Home Smart Home n n n Learning of inhabitant patterns Learn optimal automation strategies Goals n n n Maximize comfort and productivity Minimize cost Ensure security http: //ranger. uta. edu/smarthome/

TCU Smart Home n Inhabitant Prediction n Smart entertainment control n Smart kitchen recipe services n Household staff modeling n http: //personal. tcu. edu/~lburnell/crescent/cre scent. html

General Electric Smart Home n n n n Appliance control interfaces Climate control Energy management devices Lighting control Security systems Consumer Electronics Bus (CEBus) http: //www. geindustrial. com/cwc/home

Microsoft Easy Living n Camera-based person detection and tracking n Geometric world modeling for context n Multimodal sensing n Biometric authentication n Distributed systems n Ubiquitous computing n http: //research. microsoft. com/easyliving/

Philips Vision of the Future n Less obtrusive technology n Technology devices n n Interactive wallpaper n Control wands n Intelligent garbage can http: //www. design. philips. com/vof

Verizon Connected Family n Remote monitoring of the home n Entry authentication n Integrated, pervasive communications n Centralized data management

Challenges in Intelligent Environments n n n n n Home design and sensor layout Communication and pervasive computing Natural interfaces Management of available data Capture and interpretation of tasks Decision making for automation Robotic control Large-scale integration Inhabitant privacy

Sensors n How many and what type? n How to interpret sensor data? n How to interface with sensors? n Are sensors active or passive?

Communications n What medium and protocol? n How to handle bandwidth limitations? n What structure does the communication infrastructure have?

Data Management n How to store all the data? n What data is stored? n How is data distributed to the pervasive computing infrastructure?

Prediction & Decision Making n n How to extract and represent inhabitants’ task patterns? What patterns should be maintained? How to determine the actions to automate? To what level should tasks be automated?

Automation n How are the tasks automated? n How are actuators controlled? n How is safety ensured?

System Integration n n How to achieve extensibility? Should the system be centralized or decentralized? How to integrate existing technology components? How to make integration and interface intuitive?

Privacy n How to ensure that inhabitant information remains private? n What data should be gathered? n How should personal data be maintained and used?

Course Topics n Sensing n Networking n Databases n Prediction and Data Mining n Decision Making n Robotics n Privacy Issues

Example Scenario n Smart kitchen item tracking n Sense and monitor items in the kitchen n Predict usage patterns n n Automatically generate shopping lists based on usage patterns Automatically retrieve replacement items