From manufacturing to automotive to agriculture, industrial robotic arms are one of the most common types of robots in use today.
Robotic arms, also known as articulated robotic arms, are fast, reliable, and accurate and can be programmed to do an infinite number of tasks in a variety of environments. They are used in factories to automate execution of repetitive tasks, such as applying paint to equipment or parts; in warehouses to pick, select, or sort goods from distribution conveyors to fulfill consumer orders; or in a farm field to pick and place ripe fruits onto storage trays. And as robotic technologies develop and industrial environments become more connected, the capabilities of robotic arms expand to enable new use cases and business operation models.
In the past, a robotic arm required teaching to perform narrowly defined tasks, such as picking a single type of object from a precise location with a specific orientation. Robots were not able to identify a particular type of object among many, determine an object location with some tolerance (area rather than exact position), or adjust the grasp based on object orientation.
Today, thanks to devices such as Intel® RealSense™ high-resolution depth cameras, powerful CPUs and GPUs, and AI technologies such as the Intel® Distribution of OpenVINO™ toolkit, robotic arms are augmented with the sensing and intelligence to perform new tasks. These smart, vision-augmented robots can detect objects in their surroundings, recognize them by types, and manipulate them accordingly. These capabilities allow robots to operate more accurately and more consistently, and safer and faster than before. They also expand the range of tasks that robots can accomplish.
With these advancements in machine vision, AI and network technologies, robotic arms can now see, analyze, and respond to their environments while transmitting valuable data and insights back to facility and business management systems. One area that benefits from this transformation is equipment (robot included) maintenance. The robot can compute data at the edge or transmit it to a server or the cloud for remote monitoring. This process enables predictive maintenance, which in turn helps reduce maintenance costs while improving machine uptime.