Intel

An engineer at the Southwest Research Institute never had any luck using Intel RealSense cameras. But that all changed with the D455 stereo depth camera.

In the end-of-life notice, Intel reiterated it will “continue to sell the stereo products to current distribution customers.”

In this week’s episode, Steve and Mike discuss the Intel RealSense news; the reveal of the Tesla humanoid robot, and interview Stratom CEO Mark Gordon.

Intel now says the RealSense business unit is winding down and the LiDAR, Facial Authentication and Tracking product lines will reach end of life this month. However, most of the stereo products will “continue.”

RealSense has been a go-to for industry and academia for low-cost, high-quality depth sensing.

“We are winding down our RealSense business and transitioning our computer vision talent, technology and products to focus on advancing innovative technologies that better support our core businesses and IDM 2.0 strategy.”

Intel said its new Dimensional Weight Software, which uses data from the Intel RealSense L515 lidar camera, can quickly and accurately measure boxes in a wide range of sizes for logistics providers.

Intel, Accenture, the Open University, ALYN Hospital, and Applied Brain Research are working to apply neuromorphic technology to make wheelchair-mounted robot arms more adaptable and affordable.

E-commerce order fulfillment needs speed and accuracy. RightHand Robotics chose Intel’s RealSense D415 depth cameras to collect robust data for its RightPick2 system for piece picking.

A novel system made of up neural networks powered by Intel’s Loihi neuromorphic chip could lead to better robotic senses of touch and vision, according to NUS researchers.

Violet, a new disinfection robot rapidly developed by Akara Robotics, uses Intel Movidius technology to detect humans and avoid exposure to UV radiation.

Intel shared four research papers on new edge processing techniques, including one on a raycast accelerator that could improve visual SLAM accuracy while maintaining energy efficiency.

ROScube-I includes I/O connectivity features and uses the new Foxy Fitzroy build ROS 2 to enable robotics developers to quickly build, scale, and deploy AI robots such as AMRs at the edge, says ADLINK.

Machine learning on edge devices could transform the manufacturing, healthcare, and energy industries. An AI executive explains why and the hardware involved.

Pensa Systems said its approach, which combines drones, machine vision, and AI, can affordably help retailers and brands solve the $1 trillion stockout problem.

The global robotics market will continue to be affected by China’s manufacturing slowdown and trade tensions with the U.S., says international analyst Georg Stieler as he looks ahead to 2020.

Intel unveiled its 8 million-neuron neuromorphic system codenamed Pohoiki Beach today at the Defense Advanced Research Projects Agency (DARPA) Electronics Resurgence Initiative in Detroit. Consisting of 64 Loihi research chips, Intel claims Pohoiki Beach can be up to 1,000 times faster and 10,000 times more efficient than CPUs for autonomous driving, robotics and other applications.…

Intel AI Lab is working with researchers at Oregon State, Stanford, and UC San Diego on machine learning approaches that could help robots interact with dynamic environments. They include a combined approach to reinforcement learning and PartNet, a massive dataset of 3D objects with annotated components.

To serve a widening range of applications, robots need to navigate their environments and manipulate objects with greater precision than ever before. At the Robotics Summit & Expo Intel will explain how new technologies are emerging to help developers and users.

Despite a few high-profile failures, robotics investments kept going strong in April 2019, with funding flowing to companies working on self-driving cars, supply chain automation, and robots in healthcare.