Recent News & Events

Real-time Optimization Algorithms for Dynamic Walking, Running, and Manipulating Robots

  • Speaker:
    Scott Kuindersma
  • Event Date:
    Thursday February 5th, 2015
  • Time:
  • Location:
    108 WVH


The worlds largest technology companies and science funding agencies are investing heavily in robotics. They anticipate robots that perform work as first responders, efficiently explore the surfaces of planets, and streamline product manufacturing and delivery. However, despite the existence of incredibly capable hardware, the limitations of our best software for controlling and analyzing complex systems prevents us from unleashing these robots into the wild.

In this talk, I will describe my research on designing optimization algorithms that improve our ability to control dynamic motions in complex robots. I will present my work developing convex optimization-based controllers for whole-body locomotion and their application to Atlas, a full-scale hydraulic humanoid robot. I will also discuss results from my work developing statistical optimization algorithms for performing risk-sensitive policy search on robots that recover from impacts and manipulate dynamic objects. I will conclude with directions for future research, including adaptive and robust control for low-precision robots and achieving highly dynamic, versatile, and energy-efficient behaviors legged systems.

Brief Biography

Scott Kuindersma is a Postdoctoral Associate in the Robot Locomotion Group at MIT CSAIL. He received his PhD in Computer Science from the University of Massachusetts Amherst in 2012 where he was also a Graduate Research Fellow with NASA Johnson Space Center. His research interests broadly encompass legged robotics, optimization, control, nonlinear systems, and machine learning. He has designed and implemented control algorithms for several state-of-the-art robots including the UMass uBot, NASA’s Robonaut 2, and Boston Dynamics’ Atlas. Currently, he is the Planning and Control Lead for MIT’s DARPA Robotics Challenge team.

Northeastern Joins New Research Center on Healthy Aging

healthyaging1400-740x493Northeastern’s membership in this new Roybal Center dovetails with the university’s focus on health—one of its primary research themes—and builds upon its leadership in research on healthy aging. Photo via Istock.

North­eastern is a founding member of a new multi-​​university research center focused on healthy aging. In par­tic­ular, the center will develop and test inno­v­a­tive strate­gies to pro­mote, increase, and sus­tain phys­ical activity among middle-​​aged and older adults.

Terry Fulmer, dean of the Bouvé Col­lege of Health Sci­ences, will lead the North­eastern team involved in the Boston Roybal Center for Active Lifestyle Inter­ven­tions. The center launched this fall with sup­port from a five-​​year, $1.5 mil­lion grant from the National Insti­tute on Aging.

Based at Bran­deis Uni­ver­sity, the center will har­ness the exper­tise of its institutions—which also include Boston Uni­ver­sity, Boston Col­lege, and the Har­vard Med­ical School-​​affiliated Hebrew SeniorLife—and their inter­dis­ci­pli­nary researchers to develop and test moti­va­tional, social, and behav­ioral strate­gies to sup­port increased phys­ical activity, espe­cially for adults at high risk of poor health outcomes.

According to the World Health Orga­ni­za­tion, one in three adults world­wide is not active enough, and phys­ical activity is the fourth-​​leading risk factor for death. Phys­ical inac­tivity is cited as a key risk factor for health prob­lems ranging from car­dio­vas­cular dis­ease to diabetes.

“There are numerous health risks asso­ci­ated with a seden­tary lifestyle, par­tic­u­larly for older adults,” Fulmer said. “As a center, our goal is to work col­lab­o­ra­tively to create and advance research that pro­motes behav­ioral change and helps this pop­u­la­tion live healthier, more active lives.”

The center is testing and piloting strate­gies using a variety of per­son­al­ized and mul­ti­dis­ci­pli­nary approaches. North­eastern researchers are leading three of the center’s first five pilot projects:

• Carmen Sceppa, pro­fessor of health sci­ences, will examine whether a peer-​​led, community-​​based group group exer­cise pro­gram improves how frail, seden­tary older adults deal with their pos­i­tive and neg­a­tive emo­tions, and if so how these improved emotion-​​regulation strate­gies enhance their daily phys­ical activity and well-​​being.
• Holly Jimison, pro­fessor of the prac­tice in the Col­lege of Com­puter and Infor­ma­tion Sci­ence and the Bouvé Col­lege of Health Sci­ences, is devel­oping and pilot testing a novel and scal­able approach to aug­menting depres­sion pre­ven­tion and man­age­ment, with a focus on low-​​income older adults living inde­pen­dently at home. The project builds upon her work using an existing soft­ware plat­form for semi-​​automated remote health coaching.
• Eliz­a­beth Howard, asso­ciate pro­fessor of nursing, is imple­menting Vitalize 360, a com­pre­hen­sive assess­ment system and per­son­al­ized well­ness coaching pro­gram for vul­ner­able, low-​​income com­mu­nity dwelling older adults.

The center will work to create and advance research in this field, in addi­tion to training other aca­d­emic researchers and com­mu­nity orga­ni­za­tions to help older adults increase their activity level and lead a healthier lifestyle, Fulmer said.

There are cur­rently 13 Roybal Cen­ters nation­wide. The cen­ters were autho­rized by Con­gress in 1993 and are named for the chair of the former House Select Com­mittee on Aging, Edward R. Roybal. They are intended to develop and pilot inno­v­a­tive ideas for trans­la­tion of basic behav­ioral and social research find­ings into pro­grams and prac­tices that will improve the lives of older people and the capacity of insti­tu­tions to adapt to soci­etal aging.

Northeastern’s mem­ber­ship in this new Roybal Center dove­tails with the university’s focus on health, one of its pri­mary research themes.

Fulmer said North­eastern is excep­tion­ally well posi­tioned to con­duct use-​​inspired research across dis­ci­plines to address health and healthy aging. Building on its lead­er­ship in this area, North­eastern this fall estab­lished a center designed to advance nursing sci­en­tists’ research and effec­tive tech­nology inter­ven­tions for improving self-​​care and self-​​management for America’s older adults. The North­eastern Center for Tech­nology in Sup­port of Self Man­age­ment and Health, also known as NUCare, is sup­ported by the National Insti­tutes of Health’s National Insti­tute of Nursing Research.

Looking ahead: Fitness Tech in 2015


Fit­ness trackers accounted for more than half of the 35 mil­lion wear­able devices in use at the end of 2014, according to a report by global ana­lyst CCS Insight. Here, Stephen Intille, the co-​​founder of Northeastern’s per­sonal health infor­matics doc­toral pro­gram and an asso­ciate pro­fessor with joint appoint­ments in the Bouvé Col­lege of Health Sci­ences and the Col­lege of Com­puter and Infor­ma­tion Sci­ence, explains what we can expect from fit­ness tech in 2015.

Wearable fitness trackers, like the Jawbone UP3, FitBit Surge, and the forthcoming Apple Watch, promise to track your health 24/7 and help you reach your fitness goals. In your view, what devices will make the biggest splash in 2015?

In 2015 we are likely to see the introduction of even more watch-like devices that are capable of gathering fitness data but also serving other personal and productivity needs. Industry will compete to add an increasing number of sensors to the devices, measuring information such as body motion, location, heart rate, galvanic skin response (i.e., sweating), and skin temperature. The newest devices already have sophisticated input/output options, such as touch screens, radio frequency identification tags, and speech input, as well as audio and tactile output. The somewhat bulky devices introduced in 2013-14 will slim down and become more stylish, and developers will figure out user interface conventions that make the devices easier to use.

The biggest surprise in 2015 may not be how consumers use these devices for health, but rather an increasing awareness that the devices improve the utility of the mobile phone. A smartwatch that can automatically detect whether its user is walking, for instance, can make interaction with that person’s mobile phone more pleasant and efficient, such as by automatically changing availability states and the way in which people are notified of messages. The good news is that people will get in the habit of using these devices for everyday tasks, and that will create more opportunities to use the devices to also support health.

A recent study by PricewaterhouseCoopers found that 56 percent of respondents believe that average life expectancy will grow by 10 years due to wearable-enabled monitoring of our vital signs. With this in mind, what role do you think fitness trackers will play in the future of the healthcare industry?

Fitness trackers will definitely play a role in the future of our healthcare, as our “sick” care system transitions toward proactive, wellness-based care. Convenient, continuous, and autonomous data gathering on health-related behaviors will be necessary if we are to cost-effectively help hundreds of millions of Americans stay healthy and fit, while at the same time reducing their need for costly clinical and specialist care.

Nevertheless, the PricewaterhouseCoopers study is a somewhat troubling example of how industry and consumer enthusiasm for the commercial devices may exceed the scientific evidence demonstrating their effectiveness. Few well-designed studies have shown that use of wearable fitness technologies leads to long-term, sustainable health and sustained healthy behavior in the general population. In fact, anecdotal evidence suggests that many consumer fitness devices may be abandoned not long after purchase, relegated to the same drawers as pedometers, home exercise videos, food portion measurement cups, and weights. There is a risk that the public and business community will become prematurely disgruntled with the promise of wearable fitness technology before the truly novel uses and benefits of the technology are discovered and definitively proven. As researchers, we have our work cut out for us.

Your research focuses on how data acquired every day from miniature mobile and in-home sensors might be used to improve wellness via novel human-computer interfaces. What projects are on your 2015 to-do list?

We are working in two areas: improving health behavior measurement using mobile phones and wearable devices, and then using that information to create new just-in-time interventions that help people make and sustain desired behavior changes. In particular, we are exploring how mobile phones and smartwatches can be used to incrementally build up mathematical models of a person’s typical behavior so that we can identify habits. The phone or watch does what it can automatically, inferring some information about physical activity and sleep patterns, but it also asks for information from the person when it needs it. The trick is to figure out ways of doing this so that the user doesn’t feel burdened, even though the automatic sensing will never be perfect.

At the same time, we are developing ideas for how real-time knowledge of what the person is doing can be used to influence behavior by providing computer- and human-generated feedback timed precisely at actionable points of decision. Our goal is to create novel interventions that help people change habits and then maintain those habits for very long periods of time. We want to take advantage of the ability of the computer to patiently and ever-presently measure and model behavior and decision making, and then to use that information to intervene in a compelling way, just when a person is most receptive to help.

3Qs: Tracking the Flu

Alex VespignaniThe Cen­ters for Dis­ease Con­trol and Pre­ven­tion recently declared a flu epi­demic in the U.S., with the virus appearing in 46 states so far. Many people have stayed home sick, while offi­cials have announced that this year’s vac­cine is not as effec­tive as in years past. Alessandro Vespignani—a world-​​renowned sta­tis­tical physi­cist and the Stern­berg Dis­tin­guished Pro­fessor of Physics who holds joint appoint­ments in the Col­lege of Sci­ence, the Col­lege of Com­puter and Infor­ma­tion Sci­ence, and the Bouvé Col­lege of Health Sci­ences at Northeastern—and his team in the university’s Lab­o­ra­tory for the Mod­eling of Bio­log­ical and Socio-​​Technical Sys­tems are uti­lizing large amounts of data to model the spread of the virus and pre­dict when the out­break will begin to taper off. Here, Vespig­nani dis­cusses the sci­ence behind his pre­dic­tions and what they say about the future of this year’s flu season in Mass­a­chu­setts and beyond.

The CDC has declared a national flu epidemic. What’s your assessment of how widespread the flu has become in the U.S. this season, and the likelihood that it will continue to grow at the current rate or faster? And what might be the impact in Massachusetts, specifically?

The CDC data reports widespread activity in most of the U.S. Also, the intensity of the epidemic is remarkable, retracing the nasty season of 2012-13. However, the most recent data and forecast models are telling us that we are going through the peak right now, and that the activity will likely start decreasing in most of the U.S. This does not mean that we are “out of the woods” yet. Being at the peak of the season means we are just halfway through it. We therefore have to consider several more weeks of sustained flu activity. The usual recommendations about getting the flu shot and not going to work if you feel ill still apply in full.

Concerning Massachusetts, the flu season is seemingly following the national trend with a little delay. However, our region had a very “bumpy” 2013-14, with multiple peaks and irregular activity. Hopefully this year does not have too many surprises in store for us.

You and your colleagues around the globe recently created a tool that allows people to visually explore the flu data in several countries and from a variety of sources, including the CDC. How does this tool work and how can people use it?

We have set up a computational platform,, that allows people to follow the flu season by looking at the real-time data released by the various national flu surveillance systems and by exploring several different forecasting algorithms that project the evolution of the epidemic up to four weeks in advance. The algorithms we use for the forecast span a wide range of techniques, including dynamic generative models that take into account the geographical regions within each specific country and infer the specific epidemic parameters of the season, such as the virus transmissibility. We are considering more than half a dozen countries, including the U.S. and Canada, but we aim at expanding the platform by progressively adding new countries, models, and data. We are also opening the platform to other modeling groups and hope to aggregate more forecasting systems in it in the near future. The aim is to provide a real-time tool with which users can explore data, collect situational awareness, investigate trends, and look at forecasts generally available only to a small number of practitioners in the field. Because we’re operating in real time, we update the platform weekly and issue new forecasts concurrently with any new dataset originated from the surveillance systems. Reliable flu forecasts are still a scientific problem, and we hope that this platform will help in testing, comparing, and evaluating different techniques in different countries.

In addition to the flu, your lab has produced groundbreaking research on predicting the spread of the Ebola virus and other diseases. How do you go about creating these forecasts, and does predicting the flu present any significant challenges in particular?

We go after epidemics by developing large-scale computational epidemic models that integrate socio-demographic and mobility data of the population under study. These models are detailed down to the individual level and provide the dynamic of the epidemic by simulating the infection transmission event in the computer for millions of individuals in their social and geographical settings. In a nutshell, what we do is akin to what is done with computerized weather forecasts. The difference is that the data, model, and algorithms we use are describing the individuals and the biological processes underlying the spread of the disease instead of the physical processes of the meteorological systems.

The flu, although it is a seasonal disease that we know very well, is very elusive from a modeling perspective. It does not have a definite geographical initial condition. The dominant flu strain changes every year, and typically there are several co-circulating strains. These are some of the reasons why we do not have reliable forecasting systems in place—yet. Tools like our are the first attempt, and not the final solution, to solving the problem of real-time epidemic forecasting. Indeed, is an effort that we will continue to support so that the analysis of models, their eventual improvements, and their reliability can be evaluated over the span of several years and in a wide range of geographical and social contexts. There is a lot of work still out there waiting to be done.