Jonah Siekmann and Yesh GodseA research paper on robotics authored by computer science researchers at Oregon State University was recently named one of the top four out of more than 2,000 accepted submissions at a prestigious conference.

Students Jonah Siekmann and Yesh Godse presented their research findings at the 2021 IEEE International Conference on Robotics and Automation. In their paper, “Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Composition,” they report on their work using simulations to teach two-legged robots how to run, skip, and hop.

The paper is co-authored with Alan Fern, professor and associate head of research in the School of Electrical Engineering and Computer Science, and Jonathan Hurst, professor of mechanical engineering and robotics.

Traditionally, researchers have tried to train bipedal robots to move by first creating a “reference trajectory,” which tells the robot at each moment where its joints and velocities should be. This approach, however, doesn’t work particularly well since it is difficult to figure out the reference trajectories, and it doesn’t take into account the uneven surfaces the robot needs to deal with.

Instead, the researchers’ new approach trains the robot in simulation, and rewards the robot when it is accomplishing the goal, and gives negative rewards when it is not.

“We use an approach that simply specifies constraints on the foot forces and velocities which allows us to specify the different types of gaits and smoothly move between them,” Fern said. “This worked much better than we ever expected.”

Siekmann, a master’s degree student in robotics who earned an honors bachelor’s degree in computer science from Oregon State in 2020, provided some additional insights.

“We were trying to train a neural network to learn various bipedal behaviors from scratch without any kind of motion capture or reference to what those behaviors looked like,” Siekmann explained. “To do this, we used deep reinforcement learning that allows a neural network to maximize a reward function.”

Added Godse, “It turned out that there was a simple mathematical framework for describing the full spectrum of all bipedal gaits and their corresponding reward/cost functions.”

Godse graduated in just three years with a bachelor’s degree in computer science from Oregon State in spring 2021 and began working on robotics research as a freshman.

Both Siekmann and Godse are now working as controls engineers at Agility Robotics, the company co-founded by Hurst that develops the robots used in Oregon State’s Dynamic Robotics Lab.

Victor AgostinelliVictor Agostinelli, a doctoral student in electrical and computer engineering at Oregon State University, has been selected for the Pacific Northwest National Laboratory – Oregon State University Distinguished Graduate Research Program.

The goal of the program is to “strengthen and grow research collaborations and develop a select cohort of doctoral students in science, technology, engineering, and mathematics (STEM) fields.” Only 20 students whose research aligns with the U.S. Department of Energy’s mission are chosen for the program each year.

Agostinelli, who is advised by Lizhong Chen, an associate professor of electrical and computer engineering in the College of Engineering, works on research to optimize and automate the placement of machine learning accelerators on integrated circuits. Agostinelli’s research specifically focuses on optimizing the selection of dataflows.

“The multi-year funding allows Victor to pursue his passion in exploring the application of machine learning in computer architecture,” said Chen. “I look forward to the collaborative research that will strengthen the relationship between OSU and PNNL.”

Through the program, Agostinelli will be appointed to an assistantship at Oregon State University for two years and will then continue his research on a fellowship at PNNL for the next two years. There, he will work with a PNNL mentor while continuing to be advised by Chen.

Agostinelli, a native of Portland, Ore., earned a B.S. in electrical and computer engineering at Oregon State University, where he participated in research on robotic swarms in Professor Julie A. Adams’ Human-Machine Teaming Lab.

“Truly, the chance to collaborate with researchers at PNNL is priceless,” Agostinelli said. “I am incredibly excited to explore the bleeding edge of accelerator design and design optimization and automation.”

Eduardo Cotilla-SanchezEduardo Cotilla-Sanchez, an associate professor of electrical and computer engineering in the College of Engineering at Oregon State University, received the LatinX Champion of Champions award at a conference that celebrates and promotes the accomplishments of Black LGBTQ people in STEM fields.

The Black Queer Town Hall in STEM, organized in collaboration with the University of Pennsylvania and the University of Iowa, aims to foster community and make STEM more equitable. As the LatinX Champion of Champions awardee, Cotilla-Sanchez was invited to give a talk about his research to improve energy access in remote communities.

Cotilla-Sanchez’s research includes developing ways to use microgrids that can keep electricity running during emergencies such as storms or earthquakes. Currently, a focus of energy infrastructure investments is improving power systems resilience in urban areas, and rural communities are likely the last to have power restored. By building smaller microgrid systems in rural areas, those communities would not be reliant on the main energy grid during emergencies.

“This is essentially an environmental justice problem,” Cotilla-Sanchez said. “Everyone needs to have access to clean energy resources.” Toward this goal, he is also working on integrating marine energy into power grids as an alternative energy source for rural communities.

Because Cotilla-Sanchez works to integrate diversity, equity, and inclusion in his research, he was excited to engage with other researchers at the Black Queer Town Hall doing the same. “It was intriguing to see how people are solving research problems while working toward equity for all in STEM,” he said.

In a momentous win, 15 Oregon State University undergraduate students took the top spots in Oregon in the prestigious International Collegiate Programming Contest’s Pacific Northwest regional competition.

Shaurya Gaur, a computer science student and president of the OSU student chapter of the Association for Computing Machinery, helped organize the group’s participation in the contest.

“I competed last year and I loved working with others to solve these fun problems. Ever since, I’ve enjoyed competitive programming, and I wanted to keep doing it with my friends,” he said.

Computer science major Teresita Guzman Nader joined the competition hoping to build skills that might be valuable in a future career, and was pleased with the outcome.

“I improved my skills to work in a team of engineers, and I think this experience will help me to be a better team player in my future work environment,” she said.

While students enjoyed having the opportunity to compete, they wanted to hone their programming skills as well. “I set a goal to learn and practice new algorithms last year and there was no better way to achieve it than with the ACM club at the competition,” said computer science student and club vice president Matt Morgan.

RESULTS

ICPC Oregon Division 1

  • First place: Beavs’; DROP TABLE Teams; (Shaurya Gaur, Matt Morgan, Miklos Bowling)
  • Second place: Hacky Stack (Allen Benjamin, Arshia Soleimanimoorchehkhorti, Zachary Taylor)

ICPC Oregon Division 2

  • First place: Time Limit Exceeded (Wei Yu Tang, Jia Wei Cheng, Blake Cecil)
  • Second place: chmod 555 (Derek Williams, Teresita Guzman Nader, Milan Donhowe)
  • Third place: rm -f * (Sadie Thomas, Myles Scholz, Phillip Bindeman)

Kai Zeng, a computer science graduate student in the College of Engineering at Oregon State University, brought home first place in the Lucid Programming Competition. Zeng competed among 260 participants from across the western United States in the hackathon. The outer space-themed challenge required contestants to solve 12 mathematic and algorithm problems such as Six Degrees of Neil Armstrong and Antimatter Annihilation.

Although he hadn’t done any algorithmic problem solving for a while, Zeng decided to enter the contest just to brush up on those skills. “I think algorithm skills should be exercised regularly,” he said. “I plan to participate in more programming competitions in the future to continue to improve my thinking and coding abilities.”

Zeng is a master’s degree student with a research focus on distributed systems and machine learning, advised by Associate Professor Lizhong Chen.

“Zeng’s excellent programming skills have helped his research significantly,” said Chen.

Photo of Jacob Cook.

Jacob Cook is the definition of an overachiever. This spring he had the rare distinction of graduating with not one but two honors bachelor’s degrees from the College of Engineering at Oregon State University, in bioengineering and electrical and computer engineering, as well as a minor in computer science.

“Successful completion of a dual degree requires unparalleled dedication and discipline to meet requirements for both programs,” said Matthew Johnston, assistant professor of electrical and computer engineering.

Cook’s achievements were recognized with the Burgess/Tektronix Award, given each year by the College of Engineering to a senior who has demonstrated exceptional participation in activities beyond academic performance. 

In addition to excelling in two challenging academic programs, Cook also completed a MECOP internship, participated in research for two different labs, served as both an undergraduate learning assistant and a resident assistant, and was an active community member.

“Jacob’s dedication and productive contributions to multiple hands-on research programs is remarkable, and it speaks to his future potential for contributions to the industry,” Johnston said.

Although he put in a huge amount of work on his own, Cook says he was lucky to have had tremendous support from his family. 

“Both my parents are computer engineers who taught me great perseverance and an intense work ethic,” he said. “They raised me to do my best and encouraged me to go to college. Likewise, my grandfather was a businessman who taught me the importance of leadership and interpersonal skills for success. I cannot imagine where I would be without my family, and I wouldn’t have received this award without their help.”

The Burgess/Tektronix Award was initiated in 1990 to honor Fred Burgess, past dean of the College of Engineering. Cook received a plaque and a check for $500 and will be recognized at the fall College of Engineering Celebrate Excellence event in the fall.

Eta Kappa Nu at Oregon State University is an honor society for electrical and computer engineering majors through IEEE. At the end of each school year, the club recognizes two students with awards. This year winners were Yeojin Kim for the Robert Short TA of the Year award, and Noah Koontz for the Sophomore of the Year award.

Robert Short TA of the Year: Yeojin Kim

Photo of Yeojin Kim.

Yeojin Kim was born and grew up in Seoul, South Korea. She went to college at Sogang University where she completed a double undergraduate degree in computer science and engineering, and mathematics. She also worked as an intern for Naver, a South Korean web search engine, and as a software engineer for Qualcomm in Korea. She has served as a mentor for the Institute of International Education’s program Women Enhancing Technology to help female undergraduates studying in STEM fields.

“It is a great honor to receive this award. Sharing things I’ve learned with others during TA activities was one of the most pleasing moments,” Kim said.

Sophomore of the Year: Noah Koontz

Photo of Noah Koontz.

Noah Koontz has been fascinated with the fusion of hardware and software from an early age. In middle school he got his first Arduino and attempted to build an open-source laser tag system with it.

“I’ve been a maker ever since,” he said.

At Oregon State, he has been working at the Open Sensing Lab, which has allowed him to apply his passion and skills to solve real-world problems in agriculture — building internet-connected devices for farmers and researchers to monitor their crops.

“I will continue to seize opportunities to work with embedded systems and solve real-world problems, hopefully having fun along the way,” Koontz said.

Photo of Laurel Hopkins

Laurel Hopkins was awarded the Future Investigators in NASA Earth and Space Science and Technology fellowship to support her doctoral research to improve species distribution models. The models link environmental variables to species occurrences and are useful tools for science and conservation.

Hopkins, a graduate student of computer science in the College of Engineering at Oregon State, was inspired by a class project in which she was modeling butterfly occurrences. She realized she could improve species distribution models using deep learning methods to analyze satellite images.

“Deep learning methods are incredibly powerful in extracting semantic information from images, meaning these techniques are well suited to analyze remotely sensed data,” she said.

She will use a large dataset of NASA Landsat images to train deep networks which, based on preliminary results, she expects will produce habitat summaries that are more descriptive than traditional methods, and lead to more informative species distribution models.

 Hopkins will publicly share the image library and deep network architectures so other researchers can use them to advance ecological research.

The award is for $135,000 to support her research under the guidance of Rebecca Hutchinson, assistant professor of computer science, and of fisheries and wildlife.

“I am thrilled to be working towards better understanding how we can limit our footprint and help support biodiversity,” Hopkins said. “It is phenomenal to get this support from NASA because it means that they understand the need and importance of this area of work.”

Lizhong Chen
Lizhong Chen

Lizhong Chen, assistant professor of electrical and computer engineering in the College of Engineering at Oregon State University, joins five others this year who were inducted into the Hall of Fame of the IEEE International Symposium on High-Performance Computer Architecture. It is the top venue in the field and there are only 53 inductees in its 26-year history who meet the requirement of having at least eight publications accepted to the symposium.

“I feel honored, as most of the current members in the Hall of Fame are senior researchers who are IEEE and/or ACM Fellows,” said Chen. “I appreciate the recognition as it acknowledges my technical contribution to the computer architecture community in the past decade. It also helps to increase the visibility of Oregon State in this research field.”

Earlier this year, Chen received the Best Paper Runner-Up Award at the 2020 IEEE International Symposium on High-Performance Computer Architecture. He also received the prestigious National Science Foundation CAREER Award in 2018.

Chen is the founder and organizer of the Annual International Workshop on AI-Assisted Design for Architecture. He is a Senior Member of the IEEE and the Association for Computing Machinery, and currently serves as an associate editor of the IEEE Transactions on Computers.

Support with teaching from the undergraduate learning assistants was appreciated even more than usual spring term, as all classes switched to remote teaching due to the coronavirus pandemic. In recognition of the students’ efforts, a new award was created in the School of Electrical Engineering and Computer Science. Greg Healy and Nadia Najim received the awards this year which included a certificate and $500.


Photo of Greg Healy
Greg Healy, postbaccalaureate student in computer science.

Greg Healy holds bachelor’s and master’s degrees in civil engineering and is pursuing a degree in computer science to become a full-stack web developer. He has been the learning assistant for the web development course for the online degree program in computer science for postbaccalaureate students.

In course evaluations, the students said Healy was as the most influential component of their success. In addition to being extremely responsive to student questions, he also created video demonstrations to walk students through more challenging content. When asked by the course instructor, Eric Ianni, to review assignments and suggest improvements, Healy went one step further and designed several assignments that built to a towards a final assignment.

“Greg is a once in a lifetime undergraduate learning assistant,” Ianni said.


Photo of Nadia Najim
Nadia Najim, undergraduate in applied and computational mathematics.

Nadia Najim is a bachelor’s student in applied and computational mathematics. She has been an undergraduate learning assistant for large electrical engineering courses and served as the head assistant where she managed a team of up to 12 other assistants. Najim was nominated by four faculty who wrote in their letter that she “made sustained and absolutely outstanding contributions to the education of more than 2,000 undergraduate students.”

By creating reusable content, Najim has made an impact beyond her own interactions with students. She generated weekly topical material, including group and individual practice problems, as well as guidance and training for fellow assistants on best practices, tips, and tricks for approaching each course topic.

Najim’s skills were especially appreciated by Pallavi Dhagat, professor of electrical and computer engineering, who taught engineering fundamentals for the first time in spring term.

“All through the term, she kept ahead of me, alerting me to what was coming next in the recitation sessions, creating sample problems for help sessions before the midterm and final exams, rallying the other learning assistants and students during stressful times in the term, advising me on concepts she felt I could reinforce in my lectures and giving me valuable feedback on the length and difficulty of my exams,” Dhagat said.