Fellowship helps Cornell researcher improve personal robots
Ashutosh Saxena, assistant professor of computer science at Cornell University, has been named one of seven Microsoft Research Faculty Fellows for 2012. He hopes to use the fellowship to develop robots that can perform mundane household tasks and learn from past experiences.
Ashutosh Saxena, assistant professor of computer science at Cornell University, has been named one of seven Microsoft Research Faculty Fellows for 2012. As a Microsoft Fellow, Saxena will receive funding of $200,000 over two years to expand his effort to develop “personal robots” that can take over mundane household tasks and assist the elderly and disabled.
As director of the Cornell Personal Robotics group, Saxena has developed learning algorithms that enable personal robots to perform household tasks such as unloading items from a dishwasher and placing items in a refrigerator. In Saxena’s Robot Learning Lab in Upson Hall, graduate students are teaching robots to learn and adapt to the cluttered environments of homes, hospitals and nursing homes and the highly unstructured behavior of the humans they work with.
For example, a robot in Saxena’s lab can be shown a series of coffee cups, notice what features they all have in common and learn to recognize the next coffee cup it sees, even if it’s slightly different, and pick it up by whatever sort of handle it has. Similarly, a robot can learn to scan an unfamiliar kitchen to find the sink, dishwasher and cupboards so it knows where and how to place the cups.
Understanding what humans are doing is harder, but the researchers have taught robots to observe humans and identify a number of common activities. The next step, Saxena says, is to link perceptions with actions so a robot could, for example, notice that a patient hasn’t taken his medicine, remind him, and bring the bottle to his bedside.
The Microsoft funding has enabled Saxena to purchase a PR2 robot from Willow Garage, a company devoted to creating hardware for personal robotics research. Both Saxena and Willow Garage are proposing to make the results of this research freely available.
The new robot, dubbed “Kodiak,” is mobile, has two arms and, most importantly, provides feedback on the amount of force its hands exert so it can, for example, pick up an egg, or even slice a cucumber.
Saxena, who joined the Cornell faculty in 2009, received his B.Tech. from the Indian Institute of Technology Kanpur in 2004 and his M.S and Ph.D. from Stanford University in 2006 and 2009, respectively.
Saxena's Cornell page:
Video demonstrating Kodiak's capabilities:
- Edited by Chris Vavra, Control Engineering, www.controleng.com
See more about machine control at controleng.com/machinecontrol.
Case Study Database
Get more exposure for your case study by uploading it to the Consulting-Specifying Engineer case study database, where end-users can identify relevant solutions and explore what the experts are doing to effectively implement a variety of technology and productivity related projects.
These case studies provide examples of how knowledgeable solution providers have used technology, processes and people to create effective and successful implementations in real-world situations. Case studies can be completed by filling out a simple online form where you can outline the project title, abstract, and full story in 1500 words or less; upload photos, videos and a logo.
Click here to visit the Case Study Database and upload your case study.