ITRI Introduces Autonomous Selfie Drone and More at CES 2022
by DRONELIFE author Ian M. Crosby
Taiwan’s leading high-tech applied research institution, The Industrial Technology Research Institute (ITRI), recently showcased AI, robotics and ICT technologies at CES 2022 and on its virtual event page.
ITRI introduced the RGB-D AI Robot, the world’s first collaborative robot with integrated 3D vision, which received a CES 2022 Innovation Award. Its sensor technology mounted on a robot arm is 168 times smaller than that of comparable robots and 38.6 times faster. Intelligent 3D vision-sensing technology provides automatic three-dimensional scanning of the object area, helping the arm determine the optimal angle to lift objects based on their shape and placement. The RGB-D AI robot can be used for object sorting and packaging for intelligent automation in manufacturing and logistics industries, as well as serving customers directly in retail or service and healthcare industries.
The RGB-D AI robot also uses self-learning technology to enable fast, highly accurate 3D object searching, eliminating the need to revise control programs to teach robots to identify objects, a process that typically takes one to two weeks take. The RGD-D AI robot can adapt to changes in the production line and quickly learns the best handling strategy in less than 12 hours. As the robotic arm becomes smarter, it can automatically learn and determine the pickup or suction point for each new object, both reducing construction costs and increasing efficiency. The RGB-D AI Robot is scheduled to hit the market by March 2022.
The event also showcased the Autonomous Selfie Drone, which handles all composition, angle and lighting preparations before flying itself to take the best selfie picture determined via AI algorithms and data from essential photography techniques. Users can also set up different close-up angles, photography body ratio and compositions. The drone is able to analyze posture and head orientation to automatically adjust its own position and tilt angle to achieve the optimal composition. Relative portrait mode uses smart framing technology to analyze the user and the background, creating a natural and unobtrusive match between the subject and the environment. ITRI’s drone features fully automatic photography, intelligent aesthetic composition and direct use of the phone camera, ensuring superior resolution and eliminating the need for image format conversion.
ITRI also presented its Interactive Time Machine, the first system to use AI to generate an interactive 3D avatar from the user’s whole body and not just the face. The system is able to automatically generate a younger-looking avatar, including the user’s surroundings, and metaverses avatars to interact with players in real-time. The 3D model shown on the display reacts to the user’s movements in real time. The system allows the user to interact with a virtual self that looks younger or older, with use cases such as VR/AR/MR gaming, in-person entertainment, conference calls where people meet and interact with their 3D models, and Exhibitions for interactive activities to attract visitors.
Also on display was DNN Video Analysis OS, a front-end AI image recognition application for smart streetlights that enables instant alerts on environmental events such as illegal parking and traffic violations; ITRI’s Ultra Low Power AI Accelerator; virtualization-based fault tolerance for critical online services, preventing system service interruptions caused by hardware failure, network disconnection, or power failure; and the 5G O-RAN RIC, a 5G network management system consisting of an Open Radio Access Network (O-RAN) based intelligent 5G RAN Controller (RIC) and an Element Management System (EMS).
Read more about CES 2022: the Women to Watch in UAS Awards, SkyDrive Flying Vehicle.
Ian attended Dominican University of California where he received a BA in English in 2019. With a lifelong passion for writing and storytelling, and a keen interest in technology, he now contributes to DroneLife as a staff writer.
Miriam McNabb is Editor-in-Chief of DRONELIFE and CEO of JobForDrones, a marketplace for professional drone services, and is a fascinated observer of the burgeoning drone industry and drone regulatory environment. Miriam has authored over 3,000 articles focused on the commercial drone space and is an international speaker and recognized figure in the industry. Miriam has a degree from the University of Chicago and over 20 years of experience in high tech sales and marketing for new technologies.
For advice or writing in the drone industry email Miriam.
Subscribe to DroneLife here.