Cornell University researchers have programmed a PR-2 robot to not only carry out everyday tasks, but to anticipate human behavior and adjust its actions.
From a database of 120 3-D videos of people performing common household activities, the robot has been trained to identify human activities by tracking the movements of the body – reduced to a symbolic skeleton for easy calculation – breaking them down into sub-activities like reaching, carrying, pouring or drinking, and to associate the activities with objects.
Observing a new scene with its Microsoft Kinnect 3-D camera, the robot identifies the activities it sees, considers what uses are possible with the objects in the scene and how those uses fit with the activities; it then generates a set of possible continuations into the future – such as eating, drinking, cleaning, putting away – and finally chooses the most probable. As the action continues, it constantly updates and refines its predictions.
Images of 68 brains from the Human Connectome Project recently became available. The process was powered by highly advanced brain scanning hardware and state of the art image processing and analysis software.
To provide multiple perspectives on each brain, researchers employed several methods:
1. MRI scans provided basic structural images of the brain, providing very high resolution images of the convoluted folds of the cerebral cortex.
2. fMRI scans detected blood flow throughout the brain and showed brain activity for subjects both at rest and engaged in seven different tasks (including language, working memory, and gambling exercises).
3. Diffusion MRI tracked the movement of water molecules within brain fibers. Because water diffuses more rapidly along the length of the fibers that connect neurons than across them, this technique allows researchers to directly trace connections between sections of the brain.
Each imaging modality has its limitations, so combining them gives neuroscientists the best view of how the brain works. The data was purged of noise and artifacts, and then organized into a database.
Many neurons, especially in brain regions that perform sophisticated functions such as thinking and planning, react differently to a wide variety of stimulation.
“We started noticing early on that there are a whole bunch of neurons in the prefrontal cortex that can’t be classified in the traditional way of one message per neuron,” said Professor Earl Miller of MIT’s Picower Institute.
Miller and colleagues report that these neurons are essential for complex cognitive tasks, such as learning new behavior. Professor Stefano Fusi at Columbia University developed a computer model showing that without these neurons, the brain can learn only a handful of behavioral tasks.
As the crowdfunding of remote health devices increases, another vital sign monitor has launched on Indiegogo.
Scanadu Scout analyzes and tracks temperature, respiratory rate, blood oxygen, heart rate, blood pressure and stress trends. The company states that it accomplishes this in 10 seconds.
The device is still pre-FDA approval but quite promising. They claim that they can read systolic and diastolic blood pressure at 95% accuracy. It looks like they are not reading oxygen saturation level. We hope they’ll add it in the next version.
Already popular in Japan, today’s New York Times reports on the developing trend of robotic companions for the elderly.
A typical Japanese example is the Tsukuba University created Hybrid Assistive Limb. The battery-powered suit senses and amplifies the wearer’s muscle action when carrying or lifting heavy objects. Caregivers can also use the suit to aid them while lifting patients from a bed, and patients can wear it to support their movements. Other Japanese devices include a small, battery-powered trolley to aid independent walking; a portable, self-cleaning bedside toilet; and a monitoring robot which tracks and reports the location of dementia patients.
The Times describes several interesting US developed robots: Cody, a Georgia Tech created robotic nurse cable of bathing patients; HERB, a Carnegie Mellon developed butler which retrieves objects and cleans; Hector, a University of Reading robot which provides medication reminders, locates lost objects, and can assist in a fall; and Paro, a baby seal looking robot which calms dementia patients.