Digit | World’s First Human-Centric, Multi-Purpose Robot made for Logistics Work

Digit, the first human-centric, multi-purpose robot made for logistics work. Digit is designed from the ground up to go where people go and do useful work safely in spaces designed for people, starting with bulk material handling within warehouses and distribution centers.

Warehouse work includes many process-automated, repetitive tasks that all too often lead to injury and high turnover, leaving costly gaps in the workforce that snarl supply chains. While automation can help fill those gaps, existing automation solutions are typically single purpose, meaning companies have to onboard and maintain dozens of different solutions for different tasks, or they require expensive customization to the workspace. Watch on YouTube

Digit is multi-purpose, so it can execute a variety of tasks and adapt to many different workflows; a fleet of Digits will be able to switch between applications depending on current warehouse needs and seasonal shifts. Because Digit is also human-centric, meaning it is the size and shape of a human and is built to work in spaces designed for people, it is easy to deploy into existing warehouse operations and as-built infrastructure without costly retrofitting.

Digit incorporates decades of research, development, and scientific breakthroughs in dynamic mobility and manipulation from Agility’s team, allowing it to navigate obstacles with ease and walk on uneven surfaces in different human environments, all while handling and moving objects. Among the most exciting updates in the next generation of Digit are newly designed end effectors, or hands, that are optimized for grabbing and moving plastic totes commonly found in e-commerce and shipping warehouses, as well as a head and eyes to improve human robot interaction.

Comments

Post a Comment

Popular posts from this blog

MX-Phoenix | The tarantula-inspired robot was built by one man in his garage

Image
Norwegian engineer Kåre Halvorsen has created the MX-Phoenix, a 3D printed spider inspired hexapod robot that uses 18 different motors to crawl over uneven ground. Zenta has designed a number of hexapods and other varieties of robots over the years, including his award-winning MorpHex robots. He states his goals for this particular project: “A more dynamic gait engine and terrain adaptation. I also want a hexapod robot with a relative small body and large leg section, I’m also trying to keep the total weight as low as possible.” The robot’s tibia and body components were designed using Fusion 360 and printed on a Wanhao Duplicator i3. He then strengthened the printed ABS parts using an acetone vapor treatment. Weighing 4.76 kg (10.5 lb), the Mx-Phoenix utilizes a total of 18 Dynamixel servos from Robotis. The C++ code, which contains Zenta’s custom gait-algorithm for hexapod robots (called DynaZgait), is being run on a Teensy 3.6 MCU. The idea to design a hexapod walking robot was deve...
Read more

DRAGON | A Japanese dragon drone moves independently through the air, resembling the sinuous motion of a flying snake

Image
 The JSK Lab at the University of Tokyo has introduced a cutting-edge drone known as the "dragon drone," which is composed of multiple small drones capable of dynamic transformations. According to reports, this drone not only has the ability to alter its shape into various forms like squares or curved lines but also possesses the capability to autonomously determine the most suitable shape based on the space it needs to navigate. The acronym "DRAGON" stands for "Dual-rotor embedded multilink Robot with the Ability of multi-deGree-of-freedom aerial transformatiON." Inspired by traditional dragon kites, the design features a tail composed of interconnected smaller kites.  Watch on YouTube Each of the small drones is equipped with a pair of ducted fans that can be adjusted to direct thrust in almost any direction. Powered by an Intel Euclid dev kit and supported by a spine-mounted battery pack offering three minutes of flight time, the DRAGON drone's modu...
Read more

Google DeepMind is Using AI to Teach Robots to Play Soccer

Image
DeepMind, scientists have successfully trained low-cost humanoid robots to play 1v1 soccer. Using advanced techniques like deep reinforcement learning, the team was able to teach these robots agile skills and tactics, bringing us one step closer to having robots perform complex tasks in the real world.                                                                     Watch on YouTube The training process involved two stages, where robots first learned independent skills like getting up from the ground and scoring goals. In the second stage, these skills were combined into a single soccer-playing agent, which improved its tactics through self-play against previous versions of itself. This progress could lead to the development of advanced humanoid robots capable of performing complex tasks across various industries, su...
Read more