“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
- 2nd pivot to distance learning much smoother than the 1st, say district staffon November 27, 2020 at 10:30 am
Faribault Public Schools completed its pivot into full-time distance learning last week, and according to Director of Teaching and Learning Tracy Corcoran, it's going much smoother than the district's ...
- Heads of teachers’ unions ask for more time, flexibility in age of COVIDon November 27, 2020 at 3:33 am
Presidents of seven teachers’ unions in Franklin, Oxford and Androscoggin counties sent a letter to the Sun Journal this week, spelling out in stark terms the many travails of trying to educate ...
- Drive To Freedom in a Challenging World with Barbara Davison November 27, 2020 at 1:47 am
For individuals who are in a job that is not fulfilling, working hours that no longer suit them or feel like something is missing right now, Barbara Davis has a solution that ...
- Exposed students may quarantine at school in short-term policy OK'd by Oklahoma health officialson November 26, 2020 at 8:45 pm
In the past, if a student had tested positive for COVID-19, any students who interacted with the case — up to the entire class — would have been required to ...
- Local educators ask for more time, flexibility in age of COVIDon November 26, 2020 at 1:59 pm
The letter, titled "What's Really Happening Inside Our Schools," is signed by eight educators from seven associations across western Maine.
Go deeper with Google Headlines on:
Flexibility in learning
Go deeper with Bing News on:
- The effects of age and skill level on knee musculature co-contraction during functional activities: a systematic reviewon October 3, 2020 at 4:48 pm
Methods: A search of electronic databases was performed with the search terms specifying co-contraction (cocontract*, co-contract*, coactive* or co-activ ... This would seem to relate to a motor ...
- The New England Mindon July 30, 2019 at 5:48 pm
In 1652, John Cotton, foremost scholar and official apologist of the New England Way, died in Boston, his name a mighty one wherever Protestant learning and erudition were revered. These had been the ...
- Gallagher secures University of Tennessee with its security management platformon July 10, 2019 at 12:28 am
Gallagher would like to acknowledge the support of the University of Tennessee and their security partners Coactive Systems of Canton and ... smarter computer technologies like AI and machine learning ...
- Vicarious Learning in Organizationson January 6, 2018 at 12:05 pm
In one recent paper, integrating theories of experiential learning and symbolic interactionism, Professor Myers offers a theoretical account of coactive vicarious learning, capturing these ...
- How people can train robots for complex workon November 12, 2013 at 9:33 am
An approach called “coactive learning” lets humans give robots feedback to find the best way to do a job, report engineers. “We give the robot a lot of flexibility in learning,” says ...