Caltech Researcher Strives to Take Robotics to Next Level

Challenges amuse Aaron Ames. From the time he entered St. Thomas University as a student who was not completely prepared for college, Ames has evolved into an expert in the robotics forefront, running a robotics lab out of Caltech and partnering with organizations such as Amazon, Disney, and NASA. He credits St. Thomas in assisting him with this evolution.

Aaron Ames ’01 with robot CASSIE. (Image credit: Caltech)

The focus Ames’ present study with the DURUS project is on developing robotics emulating human walk. He approaches his study from a math perspective, developing theories that are subsequently applied to bipedal robots. The study has prospective implications for individualized and highly adaptable prosthetics.

It’s incredibly rewarding when you see a robot move according to something you came up with in your head. It’s a unique feeling. It started out on a piece of a paper and a pen, and it ended up making a robot walk. When you show that video, or the robot runs because of the math, and people think that’s cool, that’s equally rewarding.

Aaron Ames

St. Thomas Faculty See Potential

According to Ames, during high-school days, many of his teachers did not know how to deal with him. He said that upon entering college, he was an OK student who was not completely sure of what he wanted to major in. However, he said things took a different turn when he joined St. Thomas, since faculty there saw the potential in him. According to him, that was unbelievably remarkable and an experience he thinks he would have never gotten at other schools.

They looked at someone coming in with a nontraditional background and invested in that,” stated Ames. “The confidence they showed me influenced my understanding of myself.”

It was Jeff Jalkio, Associate Professor of Engineering, who assisted in honing Ames’ interest in engineering and had contributed robots to St. Thomas, which Ames eventually used to start a robotics lab at the university. Cheri Shakiban, Professor of Mathematics, helped Ames secure a summer research project, which transformed into a conference presentation at the International Symposium on Analysis, Combinatorics and Computing and, ultimately, a book chapter.

She saw something in me, and encouraged me to go after it and gave me all the support I needed to get there,” stated Ames. He stated the support factors played a big role in his acceptance to the University of California, Berkeley. Following graduation from St. Thomas in three years with a Bachelor of Arts in mathematics and a Bachelor of Science in mechanical engineering, he earned his PhD.

Once at Berkeley, he found that he was on par with those students whom he described as being the “best of the best,” who were from the top of their classes at MIT and Harvard, and had been undergoing training for this level of education much longer than he had.

That being said, much like at St. Thomas, when I was put in a challenging situation, I really enjoyed it,” stated Ames.

Arriving in the World of Robotics

It was at Caltech that Ames did his postdoctorate. He loved this school since it combined the positive aspects that he relished at St. Thomas and Berkeley. At the time, he knew that he would enjoy working there but also realized that the chances were “slim to none” since the school was very small.

His first teaching job was at Texas A&M, and it was there that he worked with NASA. He was involved in developing Valkyrie, a humanoid robot intended to function in damaged or degraded human-engineered environments. Since the emphasis on robotics has been ever-increasing, Ames stated that things just “blew up from there” and he was on the “front wave.”

At that time, Ames started his work on the DURUS project, which received high honors at the DARPA Robotics Challenges (DRC) courses, where DURUS took part in an endurance contest by walking on a treadmill against other robots.

If you spent any time watching the DRC, you probably noticed that all the robots walked like, you know, robots,” Evan Ackerman wrote in a review on IEEE Spectrum. “The stereotypical quasi-static robotic gait is a side effect of the robot trying to keep its center of mass balanced above its feet, which is the way to go if you’re worried about falling over all the time.”

Humans don’t walk like this. Instead, we walk by falling forward intentionally, constantly catching ourselves by taking steps. DURUS walks the same way, thanks to software controls that provide a realistic level of confidence that the robot can walk continuously without falling over.”

DURUS also won accolades when it was featured on CNN.

A Mentor for Rachel Gehlhar ’16

In 2017, Ames joined Caltech, bringing his Advanced Mechanical Experimental Robotics (AMBER) Lab with him. Although the study is evidently a profound part of his academic career, Ames stated that at Caltech, he likes the fact that he can interact with students the same way professors interacted with him at St. Thomas.

It has a personal touch. I talk to undergraduates here. I’m an adviser. For students who see the world differently, I can identify that in them and see potential, just like [St. Thomas faculty] did for me even if I didn’t fit the standard mold.

Aaron Ames

Of those working under Ames is another Tommie: Rachel Gehlhar ’16, pursuing her PhD. Jalkio was also a mentor to Gehlhar, and from her sophomore year at St. Thomas, she was sure that she wanted to join Ames’ robotics lab. Similar to Ames, Gehlhar also credited her research experience and her close relationships with faculty at St. Thomas for preparing her well.

The unique things I got were because of connections with professors,” stated Gehlhar. “I got to lead research projects and got a better view of the research process and worked closely with professors. I learned more from them and got their perspective and feedback.” That study involved working with AnnMarie Thomas, Professor of Engineering and Associate Professor of Entrepreneurship, whose mentorship she stated was the most valuable part of her St. Thomas education and had a vital role in her joining Caltech.

Gehlhar leads the prosthetics team at Caltech. At present, the team is working on a leg device that will enable amputees to adapt more easily and walk more powerfully. Her focus is on incorporating more sensors into the knee and ankle, to enable the prosthetic to have new attributes and adapt to terrain. Apart from loving the work itself, Gehlhar stated that she also relished the fact that this prosthetic has the ability to directly influence its user.

It’s exciting for me and other people to hear about my work,” stated Gehlhar. “We think about the human component in that work: How is the user going to be experiencing this? How can we take their needs and meet them with this technical field?

Apart from developing various other robots, Ames’ lab has not fallen short of probable collaborations: he has a project with the Jet Propulsion Lab for the Mars 2020 mission; in 2017, he spoke at Amazon’s conference on machine learning; and he will collaborate with Disney Research on robotics.

Among all this, in September 2017, Ames also managed to find time to give a Center for Applied Mathematics lecture at St. Thomas.

It was great coming back,” stated Ames. “Having been through a lot more since I left St. Thomas, it was cool to talk about what I’ve done and explain it to people who helped me get started.”

Cassie Goes for a Walk

Cassie Goes for a Walk. (Credit: Caltech)

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.