tapping into the potential of cobots

in rethinking robotics by Jim Lawton

Sawyer, the smart, collaborative robot from Rethink Robotics.

Joe Jones, founder of Franklin Robotics and the original inventor of iRobot’s Roomba, is currently working on a new robot that will weed your garden for you. Named Tertill, and scheduled for release in 2017, Jones’ new weed killer is one of several consumer bots coming to market that automate tasks many of us find time consuming or tedious – including mowing the lawn. Yep, you can find adaptive robots for that.

The Boston Globe gave Jones a good write up, but what I found particularly interesting is his comment: “Later models [of the Tertill] might be able to gather information and relay it to your smart phone.”

cobots: PCs with arms

At the 2016 Automatica trade fair in Germany, we saw the transition taking place in how people now understand collaborative robots (cobots) and the benefit to their businesses.

Instead of asking us questions about what is a collaborative robot, we heard lots of questions about how collaborative robots fit into the Industrial Internet of Things and Industry 4.0.

Manufacturers are still purchasing Baxter and Sawyer to perform material handling and machine tending tasks, but they’re also coming to understand the cobots can collect data, which they can correlate with other data, for actionable insights.

To use an example from the medical industry, cancer research teams have vast amounts of data regarding the progression and treatment of cancer, but for a clinical physician to wade through it all – and glean insight from it – is almost impossible.

To make sense of the data, research teams apply machine learning to detect key patterns in complex data sets. With these techniques, researchers hope to help physicians in their clinical practices make effective and accurate decisions.

It works the same for manufacturers. Yes, Baxter and Sawyer can collect data and other machines or people can analyze this data.

But what’s very exciting is that artificially intelligent robots like Baxter and Sawyer will one day have the ability to understand the tasks that need to be performed and then execute the physical steps required to get these tasks done.

The advances across the ecosystem – AI, machine learning, the IoT – are all leading us to this juncture.

Some of the advances we’ll see include:

Collecting data through sensors – Collaborative robots will see, touch and engage the ways humans do.

Taking appropriate action on data gathered – If workers are testing red parts and blue parts and the red tester breaks, the human worker can see this immediately and instruct a coworker to “send me only blue parts.” In time, a cobot will have the ability to react similarly.

Learning from their work – These adaptive robots will collect information on their own performance and provide data analysis that can inform continuous improvement.

For now, we can program Baxter or Sawyer to pack boxes and let us know through facial expressions when they get stuck. We can analyze the data they collect to see how to improve the process.

But, just as Joe Jones is creating a robot that will know the difference between your tomato seedlings and weeds – and also send you data about your soil condition and other factors – in the factory of the future manufacturers will tell a robot, “Go pack those boxes and let me know when you’re done.”

The robot will perform the task – and then give you data you might not know you needed about the process. It’s this change that has manufacturers and us excited about the future potential of cobots.

To see examples of Baxter and Sawyer on the job at customer sites, visit the Rethink Robotics video gallery. And for more headlines, videos and news about collaborative robots and automation, drop by Cobot Central. Also, subscribe above to receive blog post alerts delivered right to your inbox.


About the Author

Jim Lawton

Jim had a choice upon graduating from Tufts University – chase a dream as a concert pianist or become part of the inaugural Leaders for Manufacturing Program at MIT. He chose the latter– dedicating his career to developing and delivering innovative solutions that improve the business of manufacturing. Internally at HP, and then at breakthrough start-ups in e-commerce, inventory optimization and supply chain risk management, Jim’s never once looked back. His charter today: capture the power of data and analytics to push the standard for world-class manufacturing higher—once again.

Leave a Comment

Your email address will not be published. Required fields are marked *