Tag Archives: behavior

Stanford’s social robot ‘Jackrabbot’ seeks to understand pedestrian behavior

View video here.

The Computational Vision and Geometry Lab has developed a robot prototype that could soon autonomously move among us, following normal human social etiquettes. It’s named ‘Jackrabbot’ after the springy hares that bounce around campus.

BY VIGNESH RAMACHANDRAN


In order for robots to circulate on sidewalks and mingle with humans in other crowded places, they’ll have to understand the unwritten rules of pedestrian behavior. Stanford researchers have created a short, non-humanoid prototype of just such a moving, self-navigating machine.

The robot is nicknamed “Jackrabbot” – after the jackrabbits often seen darting across the Stanford campus – and looks like a ball on wheels. Jackrabbot is equipped with sensors to be able to understand its surroundings and navigate streets and hallways according to normal human etiquette.

The idea behind the work is that by observing how Jackrabbot navigates itself among students around the halls and sidewalks of Stanford’s School of Engineering, and over time learns unwritten conventions of these social behaviors, the researchers will gain critical insight in how to design the next generation of everyday robots such that they operate smoothly alongside humans in crowded open spaces like shopping malls or train stations.

“By learning social conventions, the robot can be part of ecosystems where humans and robots coexist,” said Silvio Savarese, an assistant professor of computer science and director of the Stanford Computational Vision and Geometry Lab.

The researchers will present their system for predicting human trajectories in crowded spaces at the Computer Vision and Pattern Recognition conference in Las Vegas on June 27.

As robotic devices become more common in human environments, it becomes increasingly important that they understand and respect human social norms, Savarese said. How should they behave in crowds? How do they share public resources, like sidewalks or parking spots? When should a robot take its turn? What are the ways people signal each other to coordinate movements and negotiate other spontaneous activities, like forming a line?

These human social conventions aren’t necessarily explicit nor are they written down complete with lane markings and traffic lights, like the traffic rules that govern the behavior of autonomous cars.

So Savarese’s lab is using machine learning techniques to create algorithms that will, in turn, allow the robot to recognize and react appropriately to unwritten rules of pedestrian traffic. The team’s computer scientists have been collecting images and video of people moving around the Stanford campus and transforming those images into coordinates. From those coordinates, they can train an algorithm.

“Our goal in this project is to actually learn those (pedestrian) rules automatically from observations – by seeing how humans behave in these kinds of social spaces,” Savarese said. “The idea is to transfer those rules into robots.”

Jackrabbot already moves automatically and can navigate without human assistance indoors, and the team members are fine-tuning the robot’s self-navigation capabilities outdoors. The next step in their research is the implementation of “social aspects” of pedestrian navigation such as deciding rights of way on the sidewalk. This work, described in their newest conference papers, has been demonstrated in computer simulations.

“We have developed a new algorithm that is able to automatically move the robot with social awareness, and we’re currently integrating that in Jackrabbot,” said Alexandre Alahi, a postdoctoral researcher in the lab.

Even though social robots may someday roam among humans, Savarese said he believes they don’t necessarily need to look like humans. Instead they should be designed to look as lovable and friendly as possible. In demos, the roughly three-foot-tall Jackrabbot roams around campus wearing a Stanford tie and sun-hat, generating hugs and curiosity from passersby.

Today, Jackrabbot is an expensive prototype. But Savarese estimates that in five or six years social robots like this could become as cheap as $500, making it possible for companies to release them to the mass market.

“It’s possible to make these robots affordable for on-campus delivery, or for aiding impaired people to navigate in a public space like a train station or for guiding people to find their way through an airport,” Savarese said.

The conference paper is titled “Social LSTM: Human Trajectory Prediction in Crowded Spaces.” See conference program for details.

Source: Stanford University News Service

How to build a proactive workforce

Building a proactive workforce is every manager’s dream as it can boost a company’s performance, but a new study has found if job satisfaction is low those ‘agents of change’ quickly lose that can-do attitude.

Researchers followed 75 workers for two years, measuring their job satisfaction levels and how proactive they were.

They found that those with high levels of job satisfaction remained proactive two years later, but those with low levels tailed off in terms of proactivity. Interestingly there was a group who had high job satisfaction but did not promote change in their organisation and still didn’t two years later.

The study by Karoline Strauss, of Warwick Business School, Mark Griffin and Sharon Parker, of University of Western Australia, and Claire Mason, of the Commonwealth Scientific and Industrial Research Organization, also looked at how adaptive workers were and discovered that the easier they adapted to change the more likely they would remain proactive over the long term.

“Proactivity is important for innovation and implementing organisational change,” said Dr Strauss, who is part of the Organisation & Human Resources Management Group at Warwick Business School.

“So it is important to sustain a proactive workforce and we have found that job satisfaction is important, not just as an instigator of proactivity, but as a force for maintaining momentum.

“There has been research showing that job satisfaction leads to a more compliant workforce, and we did find that highly satisfied employees who had not tried to promote change at work were unlikely to do so in the future. But we also found that those with high levels of job satisfaction who were proactive maintained that over two years.

“Low levels of job satisfaction may motivate high levels of proactive behaviour in the short term as workers looked to change things to become more satisfied, but this is not sustained over the long term. Our findings suggest that these workers will either succeed in changing their environment at work and so no longer see the need to seek change, or fail, become frustrated and not persevere with their proactive behaviour.”

Management research has found that effective change in an organisation requires proactivity among the workforce to be maintained over a long period. As well as job satisfaction the study on an Australian healthcare organisation, entitled Building and sustaining proactive behaviors: the role of adaptivity and job satsifaction and published in the Journal of Business and Psychology, discovered adaptability was also an important factor.

“If employees do not adapt to change, they are consequently unlikely to support proactivity,” said Dr Strauss. “This research found a significant positive link between a worker’s adaptivity and proactivity.

“Those who fail to adapt to change seem to be less likely to initiate change in the future as they may see change as threatening and may lose confidence in their own ability to be proactive. Irrespective of their past proactivity we found that employees’ proactivity may decrease if they fail to adapt to change and that may impact on a company’s performance and profitability.”

Dr Karoline Strauss also teaches Organisational Behaviour on the Warwick MBA by full-time studyWarwick Executive MBAWarwick MBA by distance learning and Global Energy MBA. She also teaches Management, Organisation and Society on Warwick Business School’s Undergraduate courses.

Source: Warwick Business School

Simple isn’t better when talking about science, Stanford philosopher suggests

Taking a philosophical approach to the assumptions that surround the study of human behavior, Stanford philosophy Professor Helen Longino suggests that no single research method is capable of answering the question of nature vs. nurture.


 

By Barbara Wilcox

Studies of the origins of human sexuality and aggression are typically in the domain of the sciences, where researchers examine genetic, neurobiological, social and environmental factors.

Behavioral research findings draw intense interest from other researchers, policymakers and the general public. But Stanford’s Helen E. Longino, the Clarence Irving Lewis Professor of Philosophy, says there’s more to the story.

Longino, who specializes in the philosophy of science, asserts in her latest book that the limitations of behavioral research are not clearly communicated in academic or popular discourse. As a result, this lack of communication distorts the scope of current behavioral research.

In her book Studying Human Behavior: How Scientists Investigate Aggression and Sexuality, Longino examines five common scientific approaches to the study of behavior – quantitative behavioral genetics, molecular behavioral genetics, developmental psychology, neurophysiology and anatomy, and social/environmental methods.

Applying the analytical tools of philosophy, Longino defines what is – and is not – measured by each of these approaches. She also reflects on how this research is depicted in academic and popular media.

In her analysis of citations of behavioral research, Longino found that the demands of journalism and of the culture at large favor science with a very simple storyline. Research that looks for a single “warrior gene” or a “gay gene,” for example, receives more attention in both popular and scholarly media than research that takes an integrative approach across scientific approaches or disciplines.

Longino spoke with the Stanford News Service about why it is important for scientists and the public to understand the parameters of behavioral research:

 

Your research suggests that social-science researchers are not adequately considering the limitations of their processes and findings. To what do you attribute this phenomenon?

The sciences have become hyper-specialized. Scientists rarely have the opportunity or support to step back from their research and ask how it connects with other work on similar topics. I see one role of philosophers of science as the provision of that larger, interpretive picture. This is not to say that there is one correct interpretation, rather that as philosophers we can show that the interpretive questions are askable.

 

Why study behavioral research through a philosophic lens?

Philosophy deals, in part, with the study of how things are known. A philosopher can ask, “What are the grounds for believing any of the claims here? What are the relationships between these approaches? The differences? What can we learn? What can this way of thinking not tell us?”

These are the questions I asked of each article I read. I developed a grid system for analyzing and recording the way the behavior under study was defined and measured, the correlational or observational data – including size and character of sample population – developed, the hypotheses evaluated.

 

What about your findings do you think would surprise people most?

I went into the project thinking that what would differentiate each approach was its definition of behavior. As the patterns emerged, I saw that. What differentiated each approach was how it characterized the range of possible causal factors.

Because each approach characterized this range differently, the measurements of different research approaches were not congruent. Thus, their results could not be combined or integrated or treated as empirical competitors. But this is what is required if the nature vs. nurture – or nature and nurture – question is to be meaningful.

I also investigated the representation of this research in public media. I found that research that locates the roots of behavior in the individual is cited far more often than population-based studies, and that research that cites genetic or neurobiological factors is cited more frequently than research into social or environmental influences on behavior. Interestingly, science journalists fairly consistently described biological studies as being more fruitful and promising than studies into social factors of behavior.

Social research was always treated as “terminally inconclusive,” using terms that amount to “we’ll never get an answer.” Biological research was always treated as being a step “on the road to knowledge.”

 

What prompted you to begin the research that became Studying Human Behavior?

In 1992, an East Coast conference on “genetic factors and crime” was derailed under pressure from activists and the Congressional Black Caucus, which feared that the findings being presented might be misused to find a racial basis for crime or links between race and intelligence. I became interested in the conceptual and theoretical foundations of the conference – the voiced and unvoiced assumptions made by both the conference participants and by the activists, policymakers and other users of the research.

 

Why did you pair human aggression and sexuality as a subject for a book?

While I started with the research on aggression, research on sexual orientation started popping up in the news and I wanted to include research on at least two behaviors or families of behavior in order to avoid being misled by potential sample bias. Of course, these behaviors are central to social life, so how we try to understand them is intrinsically interesting.

 

What could science writers be doing better?

Articles in the popular media, such as the science sections of newspapers, rarely discuss the methodology of studies that they cover as news. Yet methodology and the disciplinary approach of the scientists doing the research are critical because they frame the question.

For example, quantitative behavioral genetics research will consider a putatively shared genome against social factors such as birth order, parental environment and socioeconomic status. Molecular genetics research seeks to associate specific traits with specific alleles or combinations within the genome, but the social factors examined by quantitative behavioral genetics lie outside its purview. Neurobiological research might occupy a middle ground. But no single approach or even a combination of approaches can measure all the factors that bear on a behavior.

It’s also important to know that often, behavior is not what’s being studied. It’s a tool, not the subject. The process of serotonin re-uptake, for example, may be of primary interest to the researcher, not the behavior that it yields. Yet behavior is what’s being reported.

 

What advice do you have for people who might be concerned about potential political ramifications of research into sexuality or aggression?

I see political ramifications in what is not studied.

In studying sexual orientation, the 7-point Kinsey scale was an improvement over a previous binary measure of orientation. Researchers employing the Kinsey scale still tend to find greater concentrations at the extremes. Middle points still get dropped out of the analysis. In addition to more attention to intermediates on the scale, there could be focus on other dimensions of erotic orientation in addition to, or instead of, the sex of the individual to which one is attracted.

Similarly, there are a number of standard ways to measure aggressive response, but they are all focused on the individual. Collective action is not incorporated. If the interest in studying aggression is to shed light on crime, there’s a whole lot of behavior that falls outside that intersection, including white-collar crime and state- or military-sponsored crime.

 

What other fields of inquiry could benefit from your findings?

Climate study is as complex as behavioral study. We’d have a much better debate about climate change if we were not looking for a single answer or silver bullet. The public should understand the complexities that the IPCC [Intergovernmental Panel on Climate Change] must cope with in producing its findings.

Source: Stanford News Service