Tag Archives: psychology
#438807 Visible Touch: How Cameras Can Help ...
The dawn of the robot revolution is already here, and it is not the dystopian nightmare we imagined. Instead, it comes in the form of social robots: Autonomous robots in homes and schools, offices and public spaces, able to interact with humans and other robots in a socially acceptable, human-perceptible way to resolve tasks related to core human needs.
To design social robots that “understand” humans, robotics scientists are delving into the psychology of human communication. Researchers from Cornell University posit that embedding the sense of touch in social robots could teach them to detect physical interactions and gestures. They describe a way of doing so by relying not on touch but on vision.
A USB camera inside the robot captures shadows of hand gestures on the robot’s surface and classifies them with machine-learning software. They call this method ShadowSense, which they define as a modality between vision and touch, bringing “the high resolution and low cost of vision-sensing to the close-up sensory experience of touch.”
Touch-sensing in social or interactive robots is usually achieved with force sensors or capacitive sensors, says study co-author Guy Hoffman of the Sibley School of Mechanical and Aerospace Engineering at Cornell University. The drawback to his group’s approach has been that, even to achieve coarse spatial resolution, many sensors are needed in a small area.
However, working with non-rigid, inflatable robots, Hoffman and his co-researchers installed a consumer-grade USB camera to which they attached a fisheye lens for a wider field of vision.
“Given that the robot is already hollow, and has a soft and translucent skin, we could do touch interaction by looking at the shadows created by people touching the robot,” says Hoffman. They used deep neural networks to interpret the shadows. “And we were able to do it with very high accuracy,” he says. The robot was able to interpret six different gestures, including one- or two-handed touch, pointing, hugging and punching, with an accuracy of 87.5 to 96 percent, depending on the lighting.
This is not the first time that computer vision has been used for tactile sensing, though the scale and application of ShadowSense is unique. “Photography has been used for touch mainly in robotic grasping,” says Hoffman. By contrast, Hoffman and collaborators wanted to develop a sense that could be “felt” across the whole of the device.
The potential applications for ShadowSense include mobile robot guidance using touch, and interactive screens on soft robots. A third concerns privacy, especially in home-based social robots. “We have another paper currently under review that looks specifically at the ability to detect gestures that are further away [from the robot’s skin],” says Hoffman. This way, users would be able to cover their robot’s camera with a translucent material and still allow it to interpret actions and gestures from shadows. Thus, even though it’s prevented from capturing a high-resolution image of the user or their surrounding environment, using the right kind of training datasets, the robot can continue to monitor some kinds of non-tactile activities.
In its current iteration, Hoffman says, ShadowSense doesn’t do well in low-light conditions. Environmental noise, or shadows from surrounding objects, also interfere with image classification. Relying on one camera also means a single point of failure. “I think if this were to become a commercial product, we would probably [have to] work a little bit better on image detection,” says Hoffman.
As it was, the researchers used transfer learning—reusing a pre-trained deep-learning model in a new problem—for image analysis. “One of the problems with multi-layered neural networks is that you need a lot of training data to make accurate predictions,” says Hoffman. “Obviously, we don’t have millions of examples of people touching a hollow, inflatable robot. But we can use pre-trained networks trained on general images, which we have billions of, and we only retrain the last layers of the network using our own dataset.” Continue reading
#437820 In-Shoe Sensors and Mobile Robots Keep ...
In shoe sensor
Researchers at Stevens Institute of Technology are leveraging some of the newest mechanical and robotic technologies to help some of our oldest populations stay healthy, active, and independent.
Yi Guo, professor of electrical and computer engineering and director of the Robotics and Automation Laboratory, and Damiano Zanotto, assistant professor of mechanical engineering, and director of the Wearable Robotic Systems Laboratory, are collaborating with Ashley Lytle, assistant professor in Stevens’ College of Arts and Letters, and Ashwini K. Rao of Columbia University Medical Center, to combine an assistive mobile robot companion with wearable in-shoe sensors in a system designed to help elderly individuals maintain the balance and motion they need to thrive.
“Balance and motion can be significant issues for this population, and if elderly people fall and experience an injury, they are less likely to stay fit and exercise,” Guo said. “As a consequence, their level of fitness and performance decreases. Our mobile robot companion can help decrease the chances of falling and contribute to a healthy lifestyle by keeping their walking function at a good level.”
The mobile robots are designed to lead walking sessions and using the in-shoe sensors, monitor the user’s gait, indicate issues, and adjust the exercise speed and pace. The initiative is part of a four-year National Science Foundation research project.
“For the first time, we’re integrating our wearable sensing technology with an autonomous mobile robot,” said Zanotto, who worked with elderly people at Columbia University Medical Center for three years before coming to Stevens in 2016. “It’s exciting to be combining these different areas of expertise to leverage the strong points of wearable sensing technology, such as accurately capturing human movement, with the advantages of mobile robotics, such as much larger computational powers.”
The team is developing algorithms that fuse real-time data from smart, unobtrusive, in-shoe sensors and advanced on-board sensors to inform the robot’s navigation protocols and control the way the robot interacts with elderly individuals. It’s a promising way to assist seniors in safely doing walking exercises and maintaining their quality of life.
Bringing the benefits of the lab to life
Guo and Zanotto are working with Lytle, an expert in social and health psychology, to implement a social connectivity capability and make the bi-directional interaction between human and robot even more intuitive, engaging, and meaningful for seniors.
“Especially during COVID, it’s important for elderly people living on their own to connect socially with family and friends,” Zanotto said, “and the robot companion will also offer teleconferencing tools to provide that interaction in an intuitive and transparent way.”
“We want to use the robot for social connectedness, perhaps integrating it with a conversation agent such as Alexa,” Guo added. “The goal is to make it a companion robot that can sense, for example, that you are cooking, or you’re in the living room, and help with things you would do there.”
It’s a powerful example of how abstract concepts can have meaningful real-life benefits.
“As engineers, we tend to work in the lab, trying to optimize our algorithms and devices and technologies,” Zanotto noted, “but at the end of the day, what we do has limited value unless it has impact on real life. It’s fascinating to see how the devices and technologies we’re developing in the lab can be applied to make a difference for real people.”
Maintaining balance in a global pandemic
Although COVID-19 has delayed the planned testing at a senior center in New York City, it has not stopped the team’s progress.
“Although we can’t test on elderly populations yet, our students are still testing in the lab,” Guo said. “This summer and fall, for the first time, the students validated the system’s real-time ability to monitor and assess the dynamic margin of stability during walking—in other words, to evaluate whether the person following the robot is walking normally or has a risk of falling. They’re also designing parameters for the robot to give early warnings and feedback that help the human subjects correct posture and gait issues while walking.”
Those warnings would be literally underfoot, as the in-shoe sensors would pulse like a vibrating cell phone to deliver immediate directional information to the subject.
“We’re not the first to use this vibrotactile stimuli technology, but this application is new,” Zanotto said.
So far, the team has published papers in top robotics publication venues including IEEE Transactions on Neural Systems and Rehabilitation Engineering and the 2020 IEEE International Conference on Robotics and Automation (ICRA). It’s a big step toward realizing the synergies of bringing the technical expertise of engineers to bear on the clinical focus on biometrics—and the real lives of seniors everywhere. Continue reading
#436176 We’re Making Progress in Explainable ...
Machine learning algorithms are starting to exceed human performance in many narrow and specific domains, such as image recognition and certain types of medical diagnoses. They’re also rapidly improving in more complex domains such as generating eerily human-like text. We increasingly rely on machine learning algorithms to make decisions on a wide range of topics, from what we collectively spend billions of hours watching to who gets the job.
But machine learning algorithms cannot explain the decisions they make.
How can we justify putting these systems in charge of decisions that affect people’s lives if we don’t understand how they’re arriving at those decisions?
This desire to get more than raw numbers from machine learning algorithms has led to a renewed focus on explainable AI: algorithms that can make a decision or take an action, and tell you the reasons behind it.
What Makes You Say That?
In some circumstances, you can see a road to explainable AI already. Take OpenAI’s GTP-2 model, or IBM’s Project Debater. Both of these generate text based on a large corpus of training data, and try to make it as relevant as possible to the prompt that’s given. If these models were also able to provide a quick run-down of the top few sources in that corpus of training data they were drawing information from, it may be easier to understand where the “argument” (or poetic essay about unicorns) was coming from.
This is similar to the approach Google is now looking at for its image classifiers. Many algorithms are more sensitive to textures and the relationship between adjacent pixels in an image, rather than recognizing objects by their outlines as humans do. This leads to strange results: some algorithms can happily identify a totally scrambled image of a polar bear, but not a polar bear silhouette.
Previous attempts to make image classifiers explainable relied on significance mapping. In this method, the algorithm would highlight the areas of the image that contributed the most statistical weight to making the decision. This is usually determined by changing groups of pixels in the image and seeing which contribute to the biggest change in the algorithm’s impression of what the image is. For example, if the algorithm is trying to recognize a stop sign, changing the background is unlikely to be as important as changing the sign.
Google’s new approach changes the way that its algorithm recognizes objects, by examining them at several different resolutions and searching for matches to different “sub-objects” within the main object. You or I might recognize an ambulance from its flashing lights, its tires, and its logo; we might zoom in on the basketball held by an NBA player to deduce their occupation, and so on. By linking the overall categorization of an image to these “concepts,” the algorithm can explain its decision: I categorized this as a cat because of its tail and whiskers.
Even in this experiment, though, the “psychology” of the algorithm in decision-making is counter-intuitive. For example, in the basketball case, the most important factor in making the decision was actually the player’s jerseys rather than the basketball.
Can You Explain What You Don’t Understand?
While it may seem trivial, the conflict here is a fundamental one in approaches to artificial intelligence. Namely, how far can you get with mere statistical associations between huge sets of data, and how much do you need to introduce abstract concepts for real intelligence to arise?
At one end of the spectrum, Good Old-Fashioned AI or GOFAI dreamed up machines that would be entirely based on symbolic logic. The machine would be hard-coded with the concept of a dog, a flower, cars, and so forth, alongside all of the symbolic “rules” which we internalize, allowing us to distinguish between dogs, flowers, and cars. (You can imagine a similar approach to a conversational AI would teach it words and strict grammatical structures from the top down, rather than “learning” languages from statistical associations between letters and words in training data, as GPT-2 broadly does.)
Such a system would be able to explain itself, because it would deal in high-level, human-understandable concepts. The equation is closer to: “ball” + “stitches” + “white” = “baseball”, rather than a set of millions of numbers linking various pathways together. There are elements of GOFAI in Google’s new approach to explaining its image recognition: the new algorithm can recognize objects based on the sub-objects they contain. To do this, it requires at least a rudimentary understanding of what those sub-objects look like, and the rules that link objects to sub-objects, such as “cats have whiskers.”
The issue, of course, is the—maybe impossible—labor-intensive task of defining all these symbolic concepts and every conceivable rule that could possibly link them together by hand. The difficulty of creating systems like this, which could handle the “combinatorial explosion” present in reality, helped to lead to the first AI winter.
Meanwhile, neural networks rely on training themselves on vast sets of data. Without the “labeling” of supervised learning, this process might bear no relation to any concepts a human could understand (and therefore be utterly inexplicable).
Somewhere between these two, hope explainable AI enthusiasts, is a happy medium that can crunch colossal amounts of data, giving us all of the benefits that recent, neural-network AI has bestowed, while showing its working in terms that humans can understand.
Image Credit: Image by Seanbatty from Pixabay Continue reading