Grabbing the awkwardly shaped items that people pick up in their day-to-day lives is a slippery task for robots. Irregularly shaped items such as shoes, spray bottles, open boxes, even rubber duckies are easy for people to grab and pick up, but robots struggle with knowing where to apply a grip. In a significant step toward overcoming this problem, roboticists at UC Berkeley have a built a robot that can pick up and move unfamiliar, real-world objects with a 99 percent success rate.
DexNet 2.0 gained its highly accurate dexterity through a process called deep learning. The researchers built a vast database of three-dimensional shapes — 6.7 million data points in total — that a neural network uses to learn grasps that will pick up and move objects with irregular shapes. The neural network was then connected to a 3D sensor and a robotic arm. When an object is placed in front of DexNet 2.0, it quickly studies the shape and selects a grasp that will successfully pick up and move the object 99 percent of the time. DexNet 2.0 is also three times faster than its previous version.
DexNet 2.0 was featured as the cover story of the latest issues of MIT Technology Review, which called DexNet 2.0 “the most nimble-fingered robot yet.” The complete paper will be published in July.
Learn more: Meet the most nimble-fingered robot ever built
[osd_subscribe categories=’robots’ placeholder=’Email Address’ button_text=’Subscribe Now for any new posts on the topic “ROBOTS’]
The Latest on: Robot dexterity
- Traveling wave of light sparks simple liquid crystal microposts to perform complex dance
Reproducing similar, integrated functioning in a single synthetic material has proven difficult -few one-component materials naturally encompass the spatial and temporal coordination needed to mimic ...
- New humanoid robots closing in on humans with better dexterity
It's midnight, and the humanoid robot, its two eyes glittering in the dark, is working the graveyard shift at a railroad crossing. The scene straight out of a sci-fi movie is right around the ...
- Overcoming the challenges of bin-picking cobots
Due to the complex nature of final assembly lines, these robots were considered incapable of replicating humans’ dexterity in conducting such a task, but that is changing. Here Neil Bellinger, Head of ...
- Soft Robotics Expands 3D Vision, Soft Grasping and Artificial Intelligence Technology to Consumer Goods, E-Commerce, and Logistics
This unique solution of 3D Vision, Artificial Intelligence, and Soft Grasping gives industrial robots the dexterity and hand-eye coordination of human workers enabling their use in unstructured ...
- Autonomous Mobile Robot Market
Autonomous mobile robot market to reach $12.42 Bn in 2030, Self driving forklifts to rise at 19% CAGR; Warehouse fleet management to rake at 20% CAGR.
via Google News and Bing News