TMCnet News

ITRI Introduces Artificial Intelligence Applications for Smart Homes and Smart Cities at CES 2018
[January 08, 2018]

ITRI Introduces Artificial Intelligence Applications for Smart Homes and Smart Cities at CES 2018


CES 2018--The Industrial Technology Research Institute (News - Alert) (ITRI), Taiwan's largest and one of the world's leading high-tech applied research institutions, today announced it will introduce and demonstrate artificial-intelligence (AI) applications for smart homes and smart cities at its booth Tech East, LVCC South Hall 2 - 25611 at CES (News - Alert) 2018. Two of its AI technologies are CES 2018 Innovation Awards Honorees: The Intelligent Vision System for Companion Robots plays Scrabble; the Handheld Pesticide Residue Detector determines if the amount of pesticide residues is safe while washing fruits and vegetables and lets the user know when washing is complete. Another AI application, DeepLook, is a large-scale cloud-based video analytics technology to integrate video streaming and computing resources for video analysis and identification for tracking stolen vehicles, detecting tailgating and monitoring suspicious activities.

This press release features multimedia. View the full release here: http://www.businesswire.com/news/home/20180108005701/en/

ITRI's Intelligent Vision System for Companion Robots integrates AI, 3D vision recognition, and eye- ...

ITRI's Intelligent Vision System for Companion Robots integrates AI, 3D vision recognition, and eye-hand coordination technologies. (Photo: Business Wire)

ITRI's seven AI applications for smart homes and smart cities at CES 2018 also include: Genki Bot, which uses AI to optimize a user's sleep environment; ITRI MusicAI, which classifies musical genres and composes new music. LIM-3D, a multi-layer 3D antenna design and manufacturing technology. Optical Camera Communications (OCC) technology, which utilizes LEDs and smartphone camera to achieve visible light communications, introducing a new way of distributing and displaying information. All technologies demonstrate ITRI's innovation capability of offering breakthrough solutions for smart living.

ITRI's Intelligent Vision System for Companion Robots, a CES 2018 Innovation Awards Honoree, integrates AI, 3D vision recognition, and eye-hand coordination technologies to play Scrabble and learn from experience. ITRI's Intelligent Vision System for Companion Robots delivers the following technology breakthroughs:

  • Intelligent Vision Technology and Developmental Learning Position Detection for perception of objects: In the companion-robot demonstration at CES 2018, the robot can distinguish between various Scrabble cubes, words, and their locations. It can recognize individual letters and the words spelled by other players. The same intelligence applies in various industrial-automation and Industry 4.0 applications; for example, a robot equipped with ITRI's Intelligent Vision System could differentiate objects based on their size, positions, and surface details even if their dimensional information is similar.
  • Smart Grip Technology for interaction with objects based on perception: In addition to perceiving different objects based on size, shape, color and location, ITRI's Intelligent Vision System for Companion Robots enables a robot to grip, move and interact with the objects, while avoiding collisions with other objects. In the CES 2018 demonstrations, the robot can drive its arms to grip and move the Scrabble cubes and place them in correct cells without dropping them or hitting other cubes.
  • Deep learning: The Intelligent Vision System for Companion Robots enables a robot to adapt to changing conditions and act accordingly. In the CES 2018 Scrabble demonstration, the robot evaluates the random moves of its human opponent and moves its cubes according to its current abilities. It verifies spelling through visual input and the dictionary of its game engine, and chooses the spelling that scores highest from possible combinations.



ITRI's Handheld Pesticide Residue Detector, a CES 2018 Innovation Awards Honoree, is a portable device that can determine whether pesticide residues are within a safe range when washing fruits or vegetables. It is a breakthrough in pesticide detection for consumer use, because, until now, pesticide detection was available only through commercial laboratories. The Handheld Pesticide Detector detects eight washable pesticides from the top 10 pesticide ranking lists in the U.S. and China. If used in tandem with specialized fruit and vegetable cleansers, it can also detect fat-soluble pesticides up to a 0.5 parts-per-million (ppm) detection limit.

The Handheld Pesticide Residue Detector is easy to operate and read. The user pushes one button to activate the detector, and places the detector in water with the fruits or vegetables. The detector displays lights on the wireless charger indicating results. A red flashing light indicates danger, meaning further washing is needed; a yellow flashing light displays while washing is in progress; and a green flashing light signals that washing is complete.


The Handheld Pesticide Residue Detector includes patented technology innovations that make the portable, affordable, real-time pesticide residue detector possible. It employs a "Fabry-Perot Detection Spectrum (News - Alert) System" and a "Dynamic Degradative Algorithm."

  • Fabry-Perot Detection Spectrum System
    ITRI designed a chip based on the Fabry-Perot spectrum filter, covering multispectral absorption frequency bands of commonly used pesticides, to calculate key pesticide concentrations. Conventional optical grating for beam splitting often requires matching linear array light sensors, such as charge-coupled devices (CCDs) or contact image sensors (CISs), accompanied by higher-cost reading circuits and modules. However, the Fabry-Perot device for the conduction of beam splitting requires only one light sensor (e.g. a photodiode sensor). This not only significantly reduces system size but also decreases production cost, while enhancing the signal-to-noise ratio (SNR) of light signals. Moreover, the Fabry-Perot component is more durable against vibration or collision than conventional systems.
  • Dynamic Degradative Algorithm
    The content of the pesticide varies based on washing time for different fruits and vegetables. Therefore, ITRI's dynamic degradative algorithm was developed for real-time monitoring of the pesticide washing process. The system automatically decides whether the pesticide concentration level falls within the safety range. This algorithm effectively detects interfering sources during washing, such as water from different sources, or the presence of a fruit and vegetable cleanser (e.g. baking soda); making it easy to introduce into various household scenarios.

ITRI's DeepLook Helps Fight Crime

ITRI is also featuring at CES 2018 its game-changing technology, DeepLook, for city security surveillance. DeepLook is a large-scale cloud-based video analytical technology that integrates video streaming and computing resources. DeepLook monitors traffic activities so that public safety and law enforcement agencies can respond rapidly to reported incidents. It enables license plate recognition, video condensation, and camera network monitoring. It can track stolen vehicles or detect tailgating events. It leverages existing video surveillance infrastructure and incorporates cloud computing capabilities to enhance scalability and flexibility of incident analysis, and mass-scale video analysis, condensation, and summarization. DeepLook can integrate in seconds any video or image analytical engines (including the GPU supported AI/DNN model), and it automates and transforms time- and resource-intensive chores into ready information.

ITRI's 30-second video for CES 2018 is available here: https://www.youtube.com/watch?v=bbnXOilUY0Y.

Photos of ITRI's seven artificial intelligence applications for smart homes and smart cities at CES 2018 are available here:

ITRI's online press kit is available here: http://www.tradeshownews.com/events/ces-2018/ITRI/

Video links are available here:

Disclaimer: The CES Innovation Awards are based upon descriptive materials submitted to the judges. CTA did not verify the accuracy of any submission or of any claims made and did not test the item to which the award was given.


[ Back To TMCnet.com's Homepage ]