Penn Engineering’s Michael Posa on robots in the real world
With funding from the National Science Foundation’s CAREER Award, Posa is working on a new teaching method where robots interact with objects in the real world to build real-world intelligence via small data sets.
Robots are now helping people compose emails and vacuum their homes, but a Jetson’s-style, live-in robot to help with more complex tasks still doesn’t exist.
Michael Posa is an assistant professor in the School of Engineering and Applied Science.
(Image: Courtesy of Penn Engineering Today)
But a robot is only as smart as it is trained to be. The reason we have not yet been able to create robots with this real-world intelligence is due to the way we are teaching them. Robots currently learn through repetitive training in simulations and controlled laboratory settings. They may be great at performing an extremely precise motion over and over again, but have a hard time quickly reacting to diverse stimuli in an uncontrolled environment. To improve that ability, robots need instruction on how to process information in novel environments where there is no time or opportunity to waste.
With funding from the National Science Foundation’s CAREER Award, Posa is working on a new teaching method where robots interact with objects in the real world, and observations from those interactions are used to create a training lesson plan or model. The new approach is real-world first, simulation second, a prioritization that Posa believes is key to building robots’ real-world intelligence.
To accomplish this, robots must be equipped to learn from small data sets. Unlike machine learning models like ChatGPT, where big data sets of language, images, and video can be found on the internet, data in robotics is hard to come by. Advanced robots remain expensive and require specialized skills to operate. While shared data sets are growing in scale, they are many orders of magnitude smaller than what is available in big data sets.
“As an example, for a robot to prepare meals in the home, it must master a huge range of different foods, tools, and cooking strategies,” says Posa. “While humans intuitively understand and learn from small data—teaching a human how to prepare a meal just once or twice would be enough for them to successfully accomplish the task on their own—computers require far more repetition in an environment with little to no interruption.”
Understanding order to disorder at the atomic scale opens possibilities for next-generation electronic devices
A Penn team has developed insight into the chemical and geometric mechanisms underlying the synthesis of new 2D materials, paving the way for next-gen devices, biomedical applications, and cleaner, quicker energy conversion and storage.
Exposure to air pollution worsens Alzheimer’s disease
New research from Penn Medicine finds living in areas with high concentration of air pollution is associated with increased buildup of amyloid and tau proteins in the brains of Alzheimer’s patients, accelerating cognitive decline.
Penn buildings achieve LEED certifications, showcasing commitment to sustainability
Three recent building projects at the University of Pennsylvania have earned LEED Platinum, Gold, and Silver certifications, underscoring Penn’s ongoing commitment to sustainable design and construction.
What stiffening lung tissue reveals about the earliest stages of fibrosis
A Penn Engineering team has targeted the lung’s extracellular matrix to better understand early fibrosis by triggering the formation of special chemical bonds that increase tissue stiffness in specific locations, mimicking the first physical changes that may lead to lung fibrosis.
