Two Weeks In

continuum arm

Two weeks in to the Robotics REU here at UW Stout, I’d say things have gotten off to a very good start. I’m living in a room that’s supposed to be a double, and has AC and a view of the lake, so I can’t really complain about that. I get to try some of Wisconsin’s famed beer, which has not disappointed so far (cheese curds are next on my list). I even got to visit my first ever Catfe (a cafe where you can eat AND pet the live-in cats), which was a pretty neat experience.  One of the other things that I still really want to do is try out the on-campus disc golf course.

In terms of the project itself, I’m honestly super excited about all aspects of it. First off, I have two awesome project partners – Max and Megan – who are not only super smart and hardworking, but just generally really great people. Second, we have a super awesome project focus: a continuum robot arm! Basically, a continuum robot arm is one that features a flexible backbone supported by disks mounted at even increments, such that when the arm is actuated, the entire thing bends continuously. This is as opposed to a typical rigid, linked robot arm, that only bends at the joints in between the rigid segments (the segments themselves do not bend). Some of the primary advantages that a continuum robot arm has over a rigid arm are: 1) it has infinite degrees of freedom, meaning that it can form almost any shape, 2) it is made of generally ‘soft’ materials, meaning it cannot cause serious harm to a human, and 3) it can potentially be made at a much lower cost. Our team hopes to capitalize on all of these advantages in choosing an application for our arm, especially the fact that the arm can safely be used in the presence of humans (such robots that are capable of safe interaction with humans are also known as co-bots).

So far, our team’s primary work has been on conducting a literature review and building a second stage for the continuum arm which had been built by UW Stout students before we arrived. We’ve made good progress on both fronts, and in fact, we just finished our first iteration of the second stage today (July 10th). Of course, we weren’t able to get it quite right on our first try, so we’ll have our work cut out for us over the next several weeks (it turns out that programming controls for these kinds of arms is a rather non-trivial task, a fact which our literature review confirms). However, we are very optimistic about the progress we’ve made so far, and confident that by the end of this program, we will have a truly innovative design!

First Two Weeks – Evan Weiler

Wow! How fast two weeks can go by. I feel like I just got off the plane in Minneapolis! Being from a suburb of Los Angeles, the small town of Menomonie has been quite the change of pace from what I am used to, however it has been very welcoming! I’ve settled into the new dorm nicely and have found that the walk to the lab is not as bad as I initially thought it was going to be. There are a few cool places to eat nearby the dorm and the university which is great for when you want to get a quick bite to eat. Overall, I’m liking the area!

Contrary to what I initially expected, we were thrown into the thick of things right away. In our first week, we started by meeting with our team and our faculty advisor, ours being Dr. Cheng Liu. Dr. Liu explained to us his vision for our project this summer, which was to have robotic arm that can be controlled by inputs as seen by a camera. Our goal is to have the camera be able to recognize facial movements and use those movements to control various aspects of the arm. For example, when someone opens their mouth that could be interpreted by the robot and the robotic arm could bring a spoon with food on it to the user.

There are two different ways we can approach this, both involving computer vision. The first is through an FPGA board. This is the method that we have initially begun testing. Currently, we have created a program that can recognize which third of the screen a certain-colored object is and output to one of three bits accordingly. We plan to use this to create a line-following robot, and hope to have this done by the middle to end of this upcoming week. The second method to recognizing facial inputs is through OpenCV which is hosted on Linux through a board called the Beaglebone Black. The advantages of using OpenCV is the fact that there are many open source libraries available. Despite this, working through OpenCV will be slower than working through an FPGA because of the overhead that comes from running Linux. Computations will take longer which is a problem as our project involves real-time inputs. We plan on exploring these advantages and disadvantages in the upcoming weeks.

Update 1 – Megan

The first two weeks of the program flew by, and I feel like I’ve already gotten so much out of it. UW-Stout’s campus is really nice and small enough that most things are within walking distance. There are also a lot of neat little cafes and restaurants around campus, and we’ve had a lot of fun trying some of them out. I’m already a regular at Tabby’s Catfe! Another thing I’ve noticed since I’ve been here is that everyone is really friendly. From the students working the front desk at Fleming-Hovlid to the lab managers, everyone has been fun to talk to and very helpful in answering any questions we’ve asked. So far I’m really enjoying getting to know the area and my fellow researchers.

Within the first few days of arriving in Menomonie, my group had already received our first task. We were given a functional continuum robotic arm and instructed to improve upon it by adding a second segment, all the while brainstorming potential uses for the final product. The past several days have been spent working on this task. We began by re-wiring and re-programming the arm to make its motion and control a little bit more intuitive. In the process, we have also come up with the design for the second segment of the arm. Having printed or ordered the necessary parts, we are now in the final stages of assembling this segment and hope to have it completed within the next couple days.

With the robot nearing completion, we will soon need to decide upon an application for it. This is where our tour of the Stout Vocational Rehabilitation Institute has proven very useful. We were able to learn about a lot of existing assistive technology and begin to think about what sort of place our robot might hold in this field. As a robotic arm is certainly nothing new, our robot’s inherent safety and low cost will be its main selling points in how it furthers the state of the art. Our hopes are that our robot will be able to help people in rehabilitation or those individuals with disabilities accomplish day-to-day tasks without human assistance, thus giving them increased independence. Our options are currently restricted by the robot’s limited payload capacity and lack of an adaptive gripping mechanism. Therefore, a big decision we will have to make in the near future is whether we want to put the time and energy into eliminating these limitations or simply use our current prototype as a proof of concept, hopefully paving the way for further development in the future.

Impressions and Our Project’s Goals – Quoc Pham

I’m really enjoying my first couple of weeks here at UW Stout’s Robotics REU. The program kicks off very quickly, and the research team was already able to start testing some ideas by the end of the first week. I like that it puts a lot of the responsibility on the undergraduate researchers to take charge of our project as well as allow us to manage our own deadlines.

The walk from UW Stout’s campus to our dorms bypasses a good number of restaurants and shops yet is still only ~10 mins walk. This makes it convenient to grab breakfast, lunch, and even dinner from work and home. Though I haven’t fully explored the city of Menomonie, the lakeside view from the dorm makes for a nice scenic welcoming coming back from the lab.

At the robotics research lab, my team and I are hoping to autonomously control a robotic arm using a camera. We want the arm to be able to feed a person. This means that the robot must be able to determine when they’re ready for a bite, where the food is, how to grab it, etc. Specifically, our team is tackling the topic of object detection so the software has to be able to locate the mouth and identify if it’s open. If successful, the concept could be applied to a number of other assistive applications, like picking up things around a wheelchair, and non-assistive applications, like picking up litter. The plan is to first get successful camera-servomotor control on one of the boards, then use open source computer vision libraries since our Beaglebone board runs Linux.

There can be noticeable benefits when implementing computer vision (CV) on an FPGA as opposed to a compact computer like a Beaglebone Black. The FPGA offers parallel programming as opposed the CPU’s serial programming, which can help to speed up the processing speed. In addition, the Beaglebone runs an operating system (Linux) which means there’s more overhead to the computations, which slows down the general process. The reason the processing speed is important to computer vision is due to the real-time component of the task. A robotic arm holding a spoon in your face, for instance, has to avoid jabbing you if you’re not perfectly still. Although the FPGA can be faster, it doesn’t have an extensive library like the Beaglebone Black does due to the computer vision’s open source community. All that extra work from other developers can help us go a long way in accomplishing our goals.

In our first week, we developed a method in SystemVerilog to use the color red to send a stop output signal. Then in our second week, we expanded upon that so it can send different output signals depending on where the color red was on the screen. I learned while working on improving the robustness of the color detection that there was a lot of uncertainty in the real world. Though we eventually got the values to a satisfying performance, it took lots of trial and error due to the difficulty in debugging since we couldn’t read out individual pixel RGB values to see what we’re getting in real-time. Currently, my team is working on porting the basic algorithm over to a tiny FPGA board that will power a small mobile robot to follow red signs or tape.

Since our ultimate goal is to implement computer vision, our next step will be to experiment with the computer vision’s open source library and develop one specifically to detect a mouth. We hope to get our robot moving by Wednesday or Thursday so we can start tinkering on the Beaglebone on Friday.

Hope you enjoyed reading!

Continuum Robot Update 1

The first two weeks of the program are finished and it seems like we’ve just begun. I mainly spent the first week after arrival getting myself oriented to Menomonie and meeting my fellow researchers. Towards the end of our first week, Megan, Ryan, and I met with Devin for the first time to start to figure out the direction for our project. We are working on augmenting an existing prototype continuum robotic arm with a second segment and looking into applications for this “snake-like” robot. We are particularly interested in using this technology to build robots that can work closely alongside humans, due to the intrinsic safety of soft robots. Specifically, our team is looking to develop our current prototype for use in assistive technology and rehabilitation. We would like to be able to use our arm to help people who have lost range of motion in their upper extremities, and are currently investigating who our target audience may be.

On the more technical side of things, my main job for the last week has been a complete overhaul of the existing electronics system on the prototype. I both simplified the existing system and added the necessary extra components to control the second segment (which should be completed relatively soon). I also worked alongside Megan on some of the control aspects of the arm. Additionally the prototype (including the arduinos) is now powered using an old ATX power supply which can deliver the necessary current to run both segments concurrently.

Our research prospects for this summer look bright, and we are well on our way to completing a project by the end of this program. Hopefully things continue to go well and we can produce something that truly furthers the state of the art in continuum robotics.

Update 1 – Charles

Upon landing, I had expected noticeably cooler weather than farther south, but summer was still in full force. Menomonie is a small town, which works great because you can walk pretty much anywhere you need to go. The Stout campus is also conveniently compact. The local community seems open and friendly. The big fair by a lake on the 4th of July was great fun with lots of local businesses and people.

The program itself began more open-ended than I had anticipated. We needed to choose our own project to work on during the program. This seemed daunting for the first couple of days, but once our group put a bit of planning into what we would be doing for the remainder of our time here, it started seeming like more of an entertaining challenge.

Our initial design of an adjustable seat for wheelchairs fell through due to strictly better alternatives already being available, and I was reminded that most any idea we could choose will have already been done, and with better functionality than our available time would allow us to accomplish. We looked then to improve the efficiency, cost, and convenience of general designs already circulating. We decided on a compact robotic arm system that could be affixed to the side of a wheelchair and be stored away neatly when not in use. The arm would have a rack and pinion lift system for vertical reach, and another horizontal track for reaching outwards. The end of the arm would have a claw or whichever manipulator was needed at the time. For my part, I will be working primarily on the electronics and power systems for the arm. We are hoping that the combination of cost-efficiency and a compact design will allow this project to act as a platform for further research down the road.

How Things Have Started – Jerica

The first two weeks of research are done and it has been an experience. My group and I found out when we got here that we would have to start our assistive robotics research from scratch. Starting research from scratch is not an easy task, but we put our heads together and got an idea. Then we found out that idea has been done cheaper and simpler, so we quickly moved on. Even though it was frustrating to find out that we aren’t as clever as we think we are, it was a great learning experience and taught us to do more research before we decided on an idea. Which I know seems like common sense, but sometimes you need to learn it the hard way.

Our project idea is a simplified robotic arm that attaches to a powered wheelchair. The platform behind this robotic arm is that is more economical than other robotic arms making it easier for people to obtain and increase general availability. My part in the project is primarily the design and assembly.

The program is much more relaxed than I had anticipated, which I’m really enjoying. It gives us a chance to set the pace so that we are learning and setting goals to meet the end timeline in a way that I haven’t yet done in previous settings. I am not having any trouble settling into the area because I live here with my husband and have the luxury of having a dog. I feel very fortunate to be able to do research on my home campus. My friends and family are here and I have access to all of my hobbies. I feel that I have the best of both worlds and I’m really grateful for that!

Update 1 for Kari

Since I have been in Menomonie, WI, the almost two weeks have flown by! Besides working, I haven’t done much mainly because the people I ask here say there is a limit to things I can do. I was very impressed with all the positive attributes about campus during the academic year there is about Stout. One thing I have been doing pretty consistently is talking to the workers at the desk in the residence hall I live in. I have met some awesome people! I really enjoy the buildings on campus and all the different labs there are to look in. The fun activity I have done in Menomonie so far was Freedom Fest on the 4th of July with some other REUer’s that included eating Nitro Ice Cream, looking at vendors, listening to live music, watching fireworks, and just hanging out by the lake.

As I am getting used to working with new people, I am really excited to start getting into the nitty gritty of our project. After some difficult time deciding on a logical project that we can make within budget and would be helpful to others, we have finally ordered all the parts we think we need to complete our simplified, cheap, robotic claw that will attach to a wheelchair. There have been a lot of robotic arms built, but our groups claw is very simple and will move vertically and horizontally controlled by a joystick being able to do some reaching that would otherwise be difficult for a person in a wheelchair.

 Since mechanically I know very little, I was not much help with the design process and finding the correct items needed for the claw. Now that I know how many motors there will be and knowing we will be using an Arduino, I can start the pseudo code of the robot. So that is what I have been refreshing my mind on and thinking about. My next step will be to figure out what components will be needed for the motors to work and work on getting a schematic drawn for that.

About Me – Quoc Pham

Hi, my name is Quoc Pham.

I’m from Chicago, Illinois, and I’m currently studying electrical engineering at the University of Urbana-Champaign.

Wisconsin-Stout’s summer REU is an amazing opportunity for me because I get to work really closely with the professors and peers, and there’s so much to learn from them. That’s not including the fact that we are working with robotics, which is the number one area of technology I’m interested in.

During this REU, I wish to learn everything about what it takes to do robotic research, as well as concepts in the field that are being tackled or explored. I hope to someday apply this experience to explore my own future robotic endeavors. While I’m here, I’ll also be roaming the beautiful town of Menomonie.

For this summer, I am looking to hone my FPGA skills and discover what the FPGA can accomplish. In addition to my technical skills, I would also like to improve soft skills such as teamwork, communication, and problem-solving.

My career goal is to become experienced enough to develop and lead some of my own robotic projects into fruition so I’m very excited to be here.

Thank you for your time!

About Me – Jerica Breen

Greeting! My name is Jerica Breen, I am student at UW-Stout working on my second Bachelor’s degree in Mechanical Engineering. My first Bachelor’s was in Athletic Training from UW-Eau Claire. When I got into the working world of athletic training I realized that I was building new braces and equipment in my head and understood then that I needed to be a part of research and development. My goal is to work with prosthetics in the future. I don’t know what I will be doing school-wise in the future because I have a bit of a unique background, I love the idea of getting a master’s or PhD in prosthetics, but if I can get to where I want to be without additional schooling, I would appreciate the break from the classroom.

What I hope to get out of this research opportunity is to broaden my base of study and get my feet wet working with other engineers of a different focus. So far in my past research and projects I have only worked with someone who was of the same major as myself and I’m excited to work my group members of different scientific fields.

When I’m not dreaming about prosthetics, I like to spend time with my husband and puppy dog (12 year-old chocolate lab, but you know they are always puppies). I enjoy many outdoor sports, backpacking, crocheting, sewing, painting, and not eating the edge pieces of brownies.brownie thief...