“The robot can learn from corrective human feedback in order to plan its actions that are suitable to the environment and the objects present.”
Cornell University engineers have taught a robot to work in a mock-supermarket checkout line, modifying a Baxter robot from Rethink Robotics in Boston to “coactively learn” from humans and make adjustments while an action is in progress.
“We give the robot a lot of flexibility in learning,” said Ashutosh Saxena, assistant professor of computer science. “The robot can learn from corrective human feedback in order to plan its actions that are suitable to the environment and the objects present.”
Saxena’s research team will report their work at the Neural Information Processing Systems conference in Lake Tahoe, Calif., Dec. 5-8.
Modern industrial robots, like those on automobile assembly lines, have no brains, just memory. An operator programs the robot to move through the desired action; the robot can then repeat the exact same action every time an object goes by.
But off the assembly line, things get complicated: A personal robot working in a home has to handle tomatoes more gently than canned goods. If it needs to pick up and use a sharp kitchen knife, it should be smart enough to keep the blade away from humans.
The Baxter’s arms have two elbows and a rotating wrist, so it’s not always obvious to a human operator how best to move the arms to accomplish a particular task. So Saxena and graduate student Ashesh Jain drew on previous work, adding programming that lets the robot plan its own motions. It displays three possible trajectories on a touch screen where the operator can select the one that looks best.
Then humans can give corrective feedback. As the robot executes its movements, the operator can intervene, manually guiding the arms to fine-tune the trajectory. The robot has what the researchers call a “zero-G” mode, where the robot’s arms hold their position against gravity but allow the operator to move them. The first correction may not be the best one, but it may be slightly better. The learning algorithm the researchers provided allows the robot to learn incrementally, refining its trajectory a little more each time the human operator makes adjustments or selects a trajectory on the touch screen. Even with weak but incrementally correct feedback from the user, the robot arrives at an optimal movement.
Go deeper with Bing News on:
Flexibility in learning
- Cultivating a philosophy of conscious leadership and continuous learning
Fast Company Executive Board member Deepti Kunupudi embraces a leadership approach that prioritizes flexibility, empathy, and trust.
- New Partnership Creates Private Microschools for Families Seeking Flexibility
Parents seeking a better education are increasingly opting for microschools which offer a student-centered, high-quality education with flexibility that is ideal for today's busy families.
- Google RSAs in 2024: Everything you need to know
The latest updates and best practices for Google responsive search ads, from single-headline ads to campaign-level assets.
- Former NBIM chief advocates for more flexibility in investment management
Knut Kjaer compares the managment of NBIM with the CPPIB and the Government of Singapre Investment Corporation ...
- Salary, flexibility: Why UAE public sector employees are moving to private firms
The UAE government employees are switching to the private firms, as both sectors now offer the same timing, flexibility and pay, according to senior Emirati officials working in the public and private ...
Go deeper with Google Headlines on:
Flexibility in learning
[google_news title=”” keyword=”flexibility in learning” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
Coactive Learning
- The Learning Network
Or is it just a distraction? By The Learning Network A collection of resources and critical-thinking questions to help students better understand the protest movement and consider the complex ...
- The Best Programs for Learning to Code
As the name implies, Code Avengers makes learning how to code as fun as learning how to be a superhero. Free demo courses and quizzes teach you the fundamentals, while the built-in text editor ...
- Machine learning - statistics & facts
What kind of AI is machine learning? Of the forms of AI used, machine learning is the simplest, but that makes it also one of the most useful. Other AI subsets include deep learning, neural ...
- Education & Learning News
Apr. 22, 2024 — Normally, a person's pupils naturally widen (or dilate) in low-light environments to allow more light into the eye. However, in a new study, researchers reported that a person's ...
- How cognitive and physical demands interact when learning to play the piano
“Learning new skills, such as reading and writing, driving a car or mastering a handstand, requires cognitive processes. We wanted to know whether the cognitive requirements are stable or ...
Go deeper with Google Headlines on:
Coactive Learning
[google_news title=”” keyword=”Coactive Learning” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]