Lab teaches robot to put down objects properly
Cornell University researchers, using a 3D camera, have taught a robot how to put down simple household objects accurately in office and home scenes.
For robots, picking up objects is easy. Putting them down – in proper context – is not so simple.
Researchers at Cornell’s Personal Robotics Laboratory, led by Ashutosh Saxena, assistant professor of computer science, has found that placing objects for robots is harder because there are many options. Drinking cups, for example, go upright when placed on a table, but must be placed upside down in a dishwasher.
In early tests, the researchers placed a plate, mug, martini glass, bowl, candy cane, disc, spoon and tuning fork on a flat surface, on a hook, in a stemware holder, in a pen holder and on several different dish racks.
The research robot surveyed its environment with a 3D camera, then it randomly tested space as suitable locations for placement. For some objects the robot tests for “caging” – the presence of vertical supports that would hold an object upright. It also gives priority to “preferred” locations: A plate goes flat on a table, but upright in a dishwasher.
After training, the Saxena lab’s robot placed objects correctly 98 percent of the time when it had seen the objects and environments previously. When working with new objects in new environments, the robots placed the objects correctly 92 percent of the time.
But first, the robot has to find the dish rack. Just as humans assess a room when walking in, the Cornell researchers (Saxena and colleague Thorsten Joachims, Cornell associate professor of computer science) have developed a system that enables a robot to scan a room and identify its objects.
Pictures from the robot’s camera are stitched together to form a 3-D image of the entire room, which is then divided into segments.
The researchers trained a robot by giving it 24 office scenes and 28 home scenes in which they had labeled most objects. The computer examines such features as color, texture and what is nearby and decides what characteristics all objects with the same label have in common. In a new environment, it compares each segment of its scan with the objects in its memory and chooses the best fit.
In tests, the robot correctly identified objects about 73 percent of the time in home scenes and 84 percent in offices. In a final test, the robot successfully located a keyboard in an unfamiliar room. Again, context gives this robot an advantage. The keyboard only shows up as a few pixels in the image, but the monitor is easily found, and the robot uses that information to locate the keyboard. Saxena will present some of this research at the Neural Information Processing Systems conference in Granada, Spain, in December 2011.
- Edited by Chris Vavra, Control Engineering, www.controleng.com
Case Study Database
Get more exposure for your case study by uploading it to the Plant Engineering 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.
2012 Salary Survey
In a year when manufacturing continued to lead the economic rebound, it makes sense that plant manager bonuses rebounded. Plant Engineering’s annual Salary Survey shows both wages and bonuses rose in 2012 after a retreat the year before.
Average salary across all job titles for plant floor management rose 3.5% to $95,446, and bonus compensation jumped to $15,162, a 4.2% increase from the 2010 level and double the 2011 total, which showed a sharp drop in bonus.