Tag Archives: engineering

Learning without a brain

Instructions for how to win a soccer game:

Score more goals than your opponent.

Sounds simple, but these instructions don’t begin to explain the complexity of soccer and are useless without knowledge of the rules of soccer or how a “goal” is “scored.” Cataloging the numerous variables and situations to win at soccer is impossible and even having all that information will not guarantee a win. Soccer takes teamwork and practice.

Researchers in robotics are trying to figure out how to make a robot learn behaviors in games such as soccer, which require collaborative and/or competitive behaviors.

How then would you teach a group of robots to play soccer? Robots don’t have “bodies,” and instructions based on human body movement are irrelevant. Robots can’t watch a game and later try some fancy footwork. Robots can’t understand English unless they are designed to. How would the robots communicate with each other on the field? If a robot team did win a soccer game, how would they know?

Multiple robot systems are already a reality in automated warehouses.

Although this is merely an illustrative example, these are the types of challenges encountered by folks working to design robots to accomplish specific tasks. The main tool for teaching a robot to do anything is machine learning. With machine learning, a roboticist can give a robot limited instructions for a task, the robot can attempt a task many times, and the roboticist can reward the robot when the task is performed successfully. This allows the robot to learn how to successfully accomplish the task and use that experience to further improve. In our soccer example, the robot team is rewarded when they score a goal, and they can get better at scoring goals and winning games.

Programming machines to automatically learn collaborative skills is very hard because the outcome depends on not only what one robot did, but what all other robots did; thus it is hard to learn who contributed the most and in what way.

Our guest this week, Yathartha Tuladhar, a PhD student studying Robotics in the College of Engineering, is focused on improving multi-robot coordination. He is investigating both how to effectively reward robots and how robot-to-robot communication can increase success. Fun fact: robots don’t use human language communication. Roboticists define a limited vocabulary of numbers or letters that can become words and allow the robots to learn their own language. Not even the roboticist will be able to decode the communication!

 

Human-Robot collaborative teams will play a crucial role in the future of search and rescue.

Yathartha is from Nepal and became interested in electrical engineering as a career that would aid infrastructure development in his country. After getting a scholarship to study electrical engineering in the US at University of Texas Arlington, he learned that electrical engineering is more than developing networks and helping buildings run on electricity. He found electrical engineering is about discovery, creation, trial, and error. Ultimately, it was an experience volunteering in a robotics lab as an undergraduate that led him to where he is today.

Tune in on Sunday at 7pm and be ready for some mind-blowing information about robots and machine learning. Listen locally to 88.7FM, stream the show live, or check out our podcast.

Can soil bacteria clean up our toxic messes?

Thousands of sites across the US are contaminated with chemical solvents that have been used for decades in industrial processes. These solvents can leach into groundwater and create plumes up to several miles long. 1,4-dioxane, a probable human carcinogen, is often present in groundwater contaminant plumes because of its historical use in degreasing heavy machinery, but it’s also present in trace amounts in products as varied as laundry detergents, deicing agents, cosmetics, and even in food.

There’s good news and bad news here: The Resource Conservation and Recovery Act, enacted in 1980, established laws for the management and disposal of hazardous wastes, meaning new releases to the environment have diminished considerably. Decontamination of chlorinated solvents often involves pumping groundwater to the surface and removing the contamination through volatilization or adsorption. However, this process is expensive, time- and energy-consuming, and ineffective at removing some chemicals, like water-soluble 1,4-dioxane.

Some jobs require the help of friends. In this case, for Hannah Rolston, a fifth-year PhD student in the Department of Environmental Engineering working with Dr. Lewis Semprini, these friends are soil bacteria that are able to naturally degrade this carcinogen. Bioremediation, or the practice of putting these bacteria to work to degrade contaminants, offers some hope in cases like these. Sometimes they can degrade certain pollutants all by themselves (called natural attenuation), but when you’re dealing with carcinogens in areas with people nearby, you want to use an engineered approach to make sure this process goes as quickly and efficiently as possible.

Hannah explained to us that not all compounds are easily degraded by bacteria, and even though some will consume 1,4-dioxane as food, environmental concentrations are not enough to sustain their growth (though remain harmful to humans). To work around this, she has been using a strategy called cometabolism. This involves adding a different carbon source into the groundwater plume for the microbes to eat–ideally, one that will cause the bacteria to produce enzymes that not only degrade the food source, but the 1,4-dioxane as well. This can be tricky, and not only in an engineering sense: you need to know enough microbial metabolism to be sure they’re not converting the hazardous compound into something even worse.

Hannah collecting groundwater samples from test wells at the OSU motor pool.

Using soil samples from two contaminated sites in Colorado and California, Hannah and the Semprini group are using isobutane (yes, the same gas you use for your camp stove) to nourish the native microbial communities so that they produce a type of enzyme called a monooxygenase. She has observed the 1,4-dioxane levels decrease in these enrichments. Preliminary work shows the bacteria convert 1,4-dioxane all the way to carbon dioxide–completely benign compared to what we started with.

Hannah began her undergraduate at Seattle University as an international studies major interested in a career in diplomacy. Feeling her first year of humanities classes provided her a wide breadth of knowledge but didn’t give her applicable skills, she transferred to environmental engineering, where she became interested in groundwater and hazardous waste remediation. After graduation, she worked for the US Army Environmental Command, working with army installations across the country to comply with environmental regulations.. When the spreadsheets and desk work didn’t quite live up to its expectations, she knew it was time to seek out graduate programs where she could put her engineering background and interest in hazardous waste remediation to work.

When she’s not tricking microbes into consuming carcinogenic contaminants, Hannah can be found road biking and doing ceramics at the OSU craft center. She is also involved in the OSU Chemical, Biological, and Environmental Engineering Graduate Student Association and the OMSI Science Communication Fellowship program. To hear more about her research and journey to graduate school, tune in to Inspiration Dissemination Sunday August 26th at 7pm on 88.7 FM, or stream the show live.

Comunicación Científica con Franco

Kristen Finch interviewing Francisco Guerrero for this special episode. (Photo by Adrian Gallo)

This week on Inspiration Dissemination we will be featuring a previous guest: Francisco Guerrero, a PhD student in the Department of Forest Engineering, Resources, and Management. Francisco’s first interview aired on October 18, 2015, and we called him back for a follow-up because he has been selected for the American Association for the Advancement of Science (AAAS) Mass Media Science and Engineering Fellowship. As a fellow, Franco will be writing feature stories about climate change and health for CNN en Español. Part of the fellowship will involve helping with film production, as well. FUN FACT last time Franco was on the show, he told us that he always wanted to be a movie producer. Franco will take this amazing opportunity during the final push for his PhD research to enhance his science communication skills and gain experience in production and video broadcasting.

This special interview will begin at 6:30 pm on May 6, 2018. We will be asking Franco about the application process, his responsibilities as a fellow, and his goals for the fellowship. After our interview with Franco, we will rebroadcast his first interview on Inspiration Dissemination at 7 pm.

Tune in to KBVR Corvallis 88.7 FM at 6:30 pm to hear about the AAAS Fellowship and learn about Franco’s research in the College of Forestry. Not a local listener? No sweat! Stream the show live on line or hear the podcast next week.

Franco wants to hear from you! Tweet him with ideas for CNN Español, specifically stories about Climate Change and Health. 

The folks behind the episode: Francisco Guerrero, Kristen Finch, and Lillian Padgitt-Cobb. (Photo by Adrian Gallo)

Workplace Woes for Women in Engineering

The human race has given rise to incredible engineering accomplishments. Some examples include an Egyptian pyramid with 2.3 million perfectly placed limestone blocks, the Great Wall of China that traverses difficult terrain and can be seen from space, or the more recent example of the SpaceX Falcon Heavy launch, sending a sports car floating through space with re-usable rockets landing back on Earth to use for a future mission. It’s no surprise that the engineering field attracts the best and brightest among us because they are innovators, problem solvers, and basically all white males. Wait – What?

Four minutes into SpaceX’s Falcon Heavy launch, the manufacturing division was shown which has errily similar demographics to the NASA space race era. via @B0yle on Feb 6th 2018

During the celebration of the Falcon Heavy launch the SpaceX guys were shown jumping for joy at the technological milestones. The same way you cringe from an oncoming car with high beams is the same way many felt about the gender imbalance that was present in the 1970’s during the NASA days and continues to persists in one of the most innovative companies the world has ever seen. For example, the 2016 film Hidden Figures began to break that mold, detailing the story of female African-American mathematicians and engineers living in the south in the 1950’s who helped propel NASA to the moon, yet few knew or acknowledged their enormous role. Since their story remained in the shadows how could a young student believe ‘I too could be a female engineer’ if they believe it’s never been done before? One’s life expectations are shaped by what they see around them, and without role models that ‘look like me’ in positions of power, how can we expect for anything to change?

Gender gap in bachelor’s degrees awarded by field of study, 1969-2009. Figure 1. Courtesy of Legewie, J., and T. DePrete. 2014. The High School Environment and the Gender Gap in the Science and Engineering. Sociology of Education. 87(4):259-280.

Our guest this evening is Andrea Haverkamp, a 2nd year PhD student in the College of Engineering, who is asking what it means to think of yourself as an engineer, and examining how the engineering culture has perpetuated the lack of diversity we see today. Of the currently active engineering professionals approximately 90% are men, university engineering programs are nearly 80% male dominated. Herein lies the paradox; girls get better grades than their male counterparts from kindergarten through high school, girls have a similar level of STEM interest as their male counterparts early in their schooling career and within the last decade women outnumber men among college graduates. Unfortunately, women significantly lag behind men in college STEM degrees and only 1 out of 6 engineering degrees are received by women.

Andrea snuggling up with her beloved dog, Spaghetti.

Andrea’s research seeks to answer what happens in the engineering workplace that continues to be unwelcoming to women; but gender cannot be taken in isolation because there is a confluence of race, socioeconomic class, and potential disabilities that color our thought process that we cannot avoid. Her work also focuses on LGBT students and a broader, more expansive, theory of gender than has been used in prior engineering research. Furthermore she is using novel approach that breaks traditional boundaries in the social sciences field that she hopes to encourage her interviewees to become an active participant and empower them to become co-authors on future research papers. This method, Community Collaborative Research, was made popular by a researcher who lived in a prison to better relate to those people in his work. How can you expect to have female engineers rise through the ranks, if there are hardly any female engineers to look up to; can you see yourself become a superhero if you’re from an underrepresented minority? A recent pop-culture example is the release of the Marvel’s Black Panther; the first film with an all black cast, predominately black writers, and directors that celebrates black culture. Here is how one fan reacted from just seeing the poster [displaying the all black cast] “This is what white people get to feel all the time? Since the beginning of cinema, you get to feel empowered like this and represented? If this is what you get to feel like all the time I would love this country too!”

There is no silver bullet that will be an overnight fix for the gender imbalance in the workplace or the salary disparity between men and women in the same job. But there are some positive examples; such as some companies are taking concrete actions to get women into leadership roles, or how the Indian Space Agency (with a recent boom in women engineers) sent a rocket to Mars that was less expensive than the making of “The Martian! Through Andrea’s research we can at least begin to systematically answer the questions of how to develop a more inclusive culture for aspiring women engineers and workplaces alike. As Jorja Smith sings in the Black Panther soundtrack, “I know that we have asked for change. Don’t be scared to put the fears to shame…”

You can listen to the show at 7PM Sunday March 4th on 88.7FM or stream the show live online!

If you want to hear more from Andrea, she also hosts her own KBVR radio show called LaborWave every other Friday at 2PM. If you want to read more about Andrea’s field, she’s on the Editorial Board for the International Journal of Engineering, Social Justice, and Peace.

How many robots does it take to screw in a light bulb?

As technology continues to improve over the coming years, we are beginning to see increased integration of robotics into our daily lives. Imagine if these robots were capable of receiving general instructions regarding a task, and they were able to learn, work, and communicate as a team to complete that task with no additional guidance. Our guest this week on Inspiration Dissemination, Connor Yates a Robotics PhD student in the College of Engineering, studies artificial intelligence and machine learning and wants to make the above hypothetical scenario a reality. Connor and other members of the Autonomous Agents and Distributed Intelligence Laboratory are keenly interested in distributed reinforcement learning, optimization, and control in large complex robotics systems. Applications of this include multi-robot coordination, mobile robot navigation, transportation systems, and intelligent energy management.

Connor Yates.

A long time Beaver and native Oregonian, Connor grew up on the eastern side of the state. His father was a botanist, which naturally translated to a lot of time spent in the woods during his childhood. This, however, did not deter his aspirations of becoming a mechanical engineer building rockets for NASA. Fast forward to his first term of undergraduate here at Oregon State University—while taking his first mechanical engineering course, he realized rocket science wasn’t the academic field he wanted to pursue. After taking numerous different courses, one piqued his interest, computer science. He then went on to flourish in the computer science program eventually meeting his current Ph.D. advisor, Dr. Kagan Tumer. Connor worked with Dr. Tumer for two of his undergraduate years, and completed his undergraduate honors thesis investigating the improvement to gauge the intent of multiple robots working together in one system.

Connor taking in a view at Glacier National Park 2017.

Currently, Connor is working on improving the ability for machines to learn by implementing a reward system; think of a “good robot” and “bad robot” system. Using computer simulations, a robot can be assigned a general task. Robots usually begin learning a task with many failed attempts, but through the reward system, good behaviors can be enforced and behaviors that do not relate to the assigned task can be discouraged. Over thousands of trials, the robot eventually learns what to do and completes the task. Simple, right? However, this becomes incredibly more complex when a team of robots are assigned to learn a task. Connor focuses on rewarding not just successful completion an assigned task, but also progress toward completing the task. For example, say you have a table that requires six robots to move. When two robots attempt the task and fail, rather than just view it as a failed task, robots are capable of learning that two robots are not enough and recruit more robots until successful completion of the task. This is seen as a step wise progression toward success rather than an all or nothing type situation. It is Connor’s hope that one day in the future a robot team could not only complete a task but also report reasons why a decision was made to complete an assigned task.

In Connor’s free time he enjoys getting involved in the many PAC courses that are offered here at Oregon State University, getting outside, and trying to teach his household robot how to bring him a beer from the fridge.

Tune in to 88.7 FM at 7:00 PM Sunday evening to hear more about Connor and his research on artificial intelligence, or stream the program live.