Category Archives: Mechanical, Industrial, and Manufacturing Engineering

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.

A Softer Side of Robots

Do me a favor: close your eyes for a few seconds and think of a robot, any robot, real or imaginary.

Done? Good. Now, that robot you thought about, what did it look like? What did it do? What was it made of? The answers to the first two questions will likely be different from person to person: perhaps a utilitarian, cylindrical robot that helps with menial tasks like cleaning and homework, or a humanoid robot, hell-bent on crushing, killing, and/or destroying humans. I’m willing to bet, however, that the majority of the answers to the last question is one word: “metal”.

Most of our images of robots, droids, and automatons (i.e. R2-D2, The Cybermen, or Wall-E), including robots that we encounter in day to day life, are made of metal, but that might change in the future. The future of robotics is not simply to make robots harder, better, faster, or stronger, but also softer. For robots that must interact with humans and other living or delicate things, they must have the capacity to be gentile.

Samantha works on the jumping spider model that mimics a jumping spider by using an air hockey table with a tethered puck with a consistent starting speed

Researchers like Samantha Hemleben are beginning to explore the world of soft robotics, creating robots that are made out of soft materials, acting through changes in air pressure. These robots could be used for tasks where a light touch is needed to avoid bruising such as human contact or fruit picking. Currently, the technology to create soft robots involves making a 3D-printed mold and then casting the silicone robot parts in those molds. If you need a robot that has both soft and firm parts, it must be designed in separate steps, reducing efficiency and effectiveness.

This is where Samantha comes in; she’s trying to optimize this process. When she started her undergrad at Wofford College, she tried out Biology, Pharmacy, and Finance, but didn’t feel challenged by them. Switching to mathematics with a computer science emphasis allowed her creativity to flourish and she was able to secure a Research Experience for Undergraduates here at OSU, modeling a robot that mimics the movements of jumping spiders. This experience heavily influenced her decision to get her Ph. D. at OSU.

Samantha is now a 2nd year Ph. D. student of Drs. Cindy Grimm and Yiğit Mengüç in Robotics (School of Mechanical, Industrial, and Manufacturing Engineering). Her research is focused on trying to understand the gradient between hard and soft materials. That is, she’s creating mathematical models of this gradient so that the manufacturing process can be optimized, and soft robots will be able to stand on solid ground.

Tune in on Sunday, July 24th at 7PM PDT on 88.7FM or stream live at http://www.orangemedianetwork.com/kbvr_fm/

Teaching Old Factories New Tricks

There’s more than one way to s 3172457 kin a cat, but you can’t teach an old dog new tricks. This just about sums up the status of modern manufacturing. Although it may make an entertaining reality show, I don’t mean to imply that factories are trying to teach old dogs new ways to skin cats.

It used to be the manufacturing process was simple, design a part and pick a material to machine it out of. In the last decade or two, major breakthroughs in engineering have led to the development of drastically different manufacturing techniques. For example, additive manufacturing (e.g. 3D printing and friction welding) can reduce material waste while still yielding a part with the same strength and functionality as other methods. Although these new methods have caught the public’s attention, they don’t always transition into factories as quickly as one might expect.

Companies tend to be slow to adopt new techniques due to the cost of retooling and a lack of good comparisons between old and new methods. Working in Karl Haapala’s lab, Harsha Malshe hopes to bring some clarity to this process with a computer program that can help companies sort through all the new manufacturing options and compare them with the tried-and-true methods. The program Harsha is helping to build, along with his colleagues in the Haapala lab, will allow engineers to submit their part designs and get out a detailed comparison of all the manufacturing options for that part. Hopefully this information will encourage companies to embrace new manufacturing technologies that save money and resources, or maybe we’ll find out that the old dog already knows the best tricks. I’m guessing the answer lies somewhere in the middle.

We’ll be talking with Harsha on this week’s episode to learn more about the rapidly changing field of manufacturing engineering.

Printing Parts for Planes and Hearts

From medical implants to aerospace engineering, Ali Davar Panah is working with new technology in incremental forming (similar to 3D printing) that might allow thermoplastics and biodegradable polymers to be customized and produced for a variety of applications. Similar to dissolving stitches, items made from biopolymers could be of great medical value. Once in the body they would serve their purpose and dissolve entirely with no surgical removal required. Biopolymer printing would also be valuable for producing any number of disposable plastic items (coffee lids or plastic silverware, for example) which would decompose completely if buried. Because this type of incremental forming is a a room temperature operation, it is also useful for producing complex geometric surfaces made from heat sensitive plastics, such as those used on the insides of airplanes or space shuttles.

Ali is a doctoral student working underneath Dr. Malhotra in the Advanced Manufacturing program here in OSU’s Mechanical Engineering department. Tonight, tune in to 88.7FM KBVR Corvallis at 7PM PST, or stream the show live online at http://kbvr.com/listen to learn more about Ali’s work and his story!