FEATURE Machine Vision
The force behind
vision-guided robots
John Ripple, industry advisor to robotics firms, discusses vision-guided robotics
T
he automation industry is experiencing an explosion in technology growth and adoption. Part of this technology is enabled
by artifi cial intelligence (AI) – solutions that are more capable and advanced than ever before.
AI is now found in a growing number of places, including warehousing and distribution, where vision systems play a key role, mainly in three primary applications:
Inspection and mapping Vision systems for inspection are used in many industrial robot applications, such as providing measurement values and outputs like “pass/fail” or “present/not present”, which then dictate the next step in a process. Similar to inspection systems but not used as much are mapping systems, where vision maps do not directly translate into machine action. Both systems can be sophisticated, but do not require AI.
Pick-and-place without deep learning Pick-and-place vision systems with limited variables are deployed on most robotic cells today. Vision cameras direct the robot’s motion through closed-loop feedback, enabling it to operate quickly, accurately and safely. These systems do not have a “learning loop” but are instead pre-programmed for a fi xed set of objects and instructions. While these systems are “smart”, they do not add intelligence and do not learn.
Pick-and-place with deep learning The most sophisticated vision systems use deep learning, also referred to as “artifi cial intelligence”. Sadly, many non-learning systems are still marketed as having
32 September 2021 | Automation
intelligent (learning) capability, leading to confusion. The deep-learning algorithms (as a subset of artifi cial intelligence) learn features invariant of objects, which then they generalise over a wide spectrum of objects. For example, through such algorithms, robots can recognise the edge of an object no matter the camera visibility or lighting conditions. All three types of vision systems include
three main elements: input (camera), processor (computer/program) and output (robot).
Basic building blocks Vision-guided robots that use deep- learning algorithms for industrial applications recognise diff erent types of packaging, locations and other variables (say, overlapping items), and act upon them. Compared to self-driving cars, some variables for industrial robots are not as complex, but the underlying approach to learning and responding quickly is the same. There are three co-dependent
requirements for deep-learning solutions: • Computer processing power; • High-quality and varied data; • Deep-learning algorithms.
Vision-guided industrial robots Commercial applications using robots to pick, place, palletise/de-palletise and more in a warehouse environment require the three basic building blocks mentioned here: cameras, software and robots. The cameras and robots are the eyes and arms; the software is the brain. All three components must work together to optimise system performance.
Camera technology enables the fl ow of
automationmagazine.co.uk
high-quality data. Cameras and post image processing provide a stream of data ready for the deep-learning algorithm to process, evaluate and turn into actionable tasks for the robots.
The robot and end eff ector (a.k.a. gripper) also play a critical role in system performance. They must provide a level of reach as well as grip strength, dexterity and speed for the application. Both, robot and end eff ector, respond to commands from the deep-learning algorithm. Hence, there are three points to remember about AI and vision-guided robotic systems:
• Deep-learning algorithms classify data in multiple categories;
• Deep-learning algorithms require both high-quality and varied data; • Algorithms become more powerful over
time.
Latest developments in camera technology and computer processing power help further advance the deep-learning software, which in turn improves robot performance. The future has arrived!
CONTACT:
Fizyr
Fizyr.com
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50
