- Ai - Engineering Mailing Lists

[CoRIS-List] Fwd: Alper Dumanli - PhD Defense - Thursday, March 18, 10am
by Hatton, Ross 16 Mar '21

16 Mar '21

*From:* "Dumanli, Alper" <dumanlia(a)oregonstate.edu> *Date:* March 15, 2021 at 8:16:44 PM PDT *To:* "Sencer, Burak" <Burak.Sencer(a)oregonstate.edu> *Subject:* *Re: Alper Dumanli - PhD Defense - Thursday, March 18, 10am* Hi all, Alper Dumanli will be defending his PhD dissertation on Thursday (March 18th) at 10am. Below are the details, hope to see you there! *Date and Time: *Thursday, March 18, 10am *Title: *Active and Passive Control of Machine Tool Vibrations for High Speed and Accuracy *Abstract:* High-performance mechatronic systems are widely used in precision manufacturing equipment such as CNC machine tools, 3D-Printers, photolithography systems, and industrial robots. To keep up with the rapidly increasing productivity and accuracy demands, it is crucial that mechatronic systems (feed drives) of these manufacturing equipment deliver high-speed motion with high precision. In this dissertation, motion control strategies are presented to increase dynamic positioning accuracy and productivity of such systems. First, a novel trajectory generation method is presented to avoid exciting low frequency structural vibration modes, without compromising from productivity. Trajectory generation problem is posed as a convex optimization problem, and a practical windowing method is presented to implement the proposed strategy in real-time for realistic manufacturing scenarios. Next, a data-driven trajectory shaping algorithm is designed to eliminate dynamic positioning errors induced by flexible motion transmission components (such as ball screw drives) and nonlinear friction forces typically caused by mechanical bearings and guiding units. The proposed algorithm is used for optimizing trajectory pre-filters through machine-in-the-loop iterations, and therefore it can be applied on a wide variety of systems without elaborate dynamic modeling. Finally, an active tool position control strategy is proposed to mitigate chatter vibrations for improving stability margins of turning processes. Two motion control algorithms are developed to control the dynamic interaction between the tool and the workpiece. Effectiveness of the proposed strategies is demonstrated on machine tools by high-speed tracking and machining experiments. *Location:* Zoom meeting link below: https://oregonstate.zoom.us/j/9759813712?pwd=aGZZSVc2ck53N3pqUW1uOGFFWXNUZz… <https://www.google.com/url?q=https://oregonstate.zoom.us/j/9759813712?pwd%3…> Password: mime97331 Phone Dial-In Information +1 971 247 1195 US (Portland) +1 253 215 8782 US (Tacoma) +1 301 715 8592 US (Washington D.C) Meeting ID: 975 981 3712

1 0

OSU AI Seminar - March 10 2021 | Yezhou Yang - Arizona State University
by Patravali, Jay Sanjay 12 Mar '21

12 Mar '21

Dear All, Our next speaker is Prof. Yezhou Yang from Arizona State University. He will be presenting *"*Visual Recognition beyond Appearances, and its Robotic Applications*"* this *Wednesday 3/10 from 1.00-2.00PM PT.* Zoom Link: https://tinyurl.com/ydf946w7 Please find attached the poster flyer for more information. *Title*: Visual Recognition beyond Appearances, and its Robotic Applications *Abstract*: The goal of Computer Vision, as coined by Marr, is to develop algorithms to answer What are Where at When from visual appearance. The speaker, among others, recognizes the importance of studying underlying entities and relations beyond visual appearance, following an Active Perception paradigm. This talk will present the speaker's efforts over the last decade, ranging from 1) reasoning beyond appearance for visual question answering, image understanding and video captioning tasks, through 2) temporal and self-supervised knowledge distillation with incremental knowledge transfer, till 3) their roles in a Robotic visual learning framework via a Robotic Indoor Object Search task. The talk will also feature the Active Perception Group (APG)’s ongoing projects (NSF RI, NRI and CPS, DARPA KAIROS, and Arizona IAM) addressing emerging challenges of the nation in autonomous driving, AI security and healthcare domains, at the ASU School of Computing, Informatics, and Decision Systems Engineering (CIDSE). *Bio*: Yezhou Yang is an Assistant Professor at School of Computing, Informatics, and Decision Systems Engineering, Arizona State University. He is directing the ASU Active Perception Group. His primary interests lie in Cognitive Robotics, Computer Vision, and Robot Vision, especially exploring visual primitives in human action understanding from visual input, grounding them by natural language as well as high-level reasoning over the primitives for intelligent robots. Before joining ASU, Dr. Yang was a Postdoctoral Research Associate at the Computer Vision Lab and the Perception and Robotics Lab, with the University of Maryland Institute for Advanced Computer Studies. He is a recipient of Qualcomm Innovation Fellowship 2011, the NSF CAREER award 2018 and the Amazon AWS Machine Learning Research Award 2019. He receives his Ph.D. from University of Maryland at College Park, and B.E. from Zhejiang University, China. Please plan on attending! Thanks, Jay Patravali Graduate Student, CoRIS-EECS. Oregon State University ---- AI Seminar Important Reminders: -> The AI Seminar has a strict "no electronics" and "no recordings" policy. -> For graduate students in the AI program, attendance is strongly encouraged.

2 1

[CoRIS-List] Robotics seminar Friday, March 12 *noon*: Chad Jenkins
by Ross Hatton 11 Mar '21

11 Mar '21

Hi All, The Robotics Today seminar series has added several talks for the spring. Tomorrow's talk, "That Ain’t Right: AI Mistakes and Black Lives" is from Professor Chad Jenkins at the University of Michigan. The talk will be streamed at noon, with details at https://roboticstoday.github.io -Ross =========== Ross L. Hatton Associate Professor, Robotics and Mechanical Engineering Collaborative Robotics and Intelligent Systems Institute (CoRIS) Oregon State University coris.oregonstate.edu research.engr.oregonstate.edu/lram/ rosslhatton.com ross.hatton(a)oregonstate.edu

2 1

OSU AI Seminar - **Today** | Yezhou Yang - Arizona State University
by Patravali, Jay Sanjay 10 Mar '21

10 Mar '21

Dear All, A gentle reminder for today's seminar by Prof. Yezhou Yang from Arizona State University. He will be presenting *"*Visual Recognition beyond Appearances, and its Robotic Applications*"* between* 1.00-2.00PM PT.* Zoom Link: https://tinyurl.com/ydf946w7 Please find attached the poster flyer for more information. *Title*: Visual Recognition beyond Appearances, and its Robotic Applications *Abstract*: The goal of Computer Vision, as coined by Marr, is to develop algorithms to answer What are Where at When from visual appearance. The speaker, among others, recognizes the importance of studying underlying entities and relations beyond visual appearance, following an Active Perception paradigm. This talk will present the speaker's efforts over the last decade, ranging from 1) reasoning beyond appearance for visual question answering, image understanding and video captioning tasks, through 2) temporal and self-supervised knowledge distillation with incremental knowledge transfer, till 3) their roles in a Robotic visual learning framework via a Robotic Indoor Object Search task. The talk will also feature the Active Perception Group (APG)’s ongoing projects (NSF RI, NRI and CPS, DARPA KAIROS, and Arizona IAM) addressing emerging challenges of the nation in autonomous driving, AI security and healthcare domains, at the ASU School of Computing, Informatics, and Decision Systems Engineering (CIDSE). *Bio*: Yezhou Yang is an Assistant Professor at School of Computing, Informatics, and Decision Systems Engineering, Arizona State University. He is directing the ASU Active Perception Group. His primary interests lie in Cognitive Robotics, Computer Vision, and Robot Vision, especially exploring visual primitives in human action understanding from visual input, grounding them by natural language as well as high-level reasoning over the primitives for intelligent robots. Before joining ASU, Dr. Yang was a Postdoctoral Research Associate at the Computer Vision Lab and the Perception and Robotics Lab, with the University of Maryland Institute for Advanced Computer Studies. He is a recipient of Qualcomm Innovation Fellowship 2011, the NSF CAREER award 2018 and the Amazon AWS Machine Learning Research Award 2019. He receives his Ph.D. from University of Maryland at College Park, and B.E. from Zhejiang University, China. Please plan on attending! Thanks, Jay Patravali Graduate Student, CoRIS-EECS. Oregon State University ---- AI Seminar Important Reminders: -> The AI Seminar has a strict "no electronics" and "no recordings" policy. -> For graduate students in the AI program, attendance is strongly encouraged.

1 0

OSU AI Seminar - **Today 1PM** | Liang Huang, Oregon State University
by Patravali, Jay Sanjay 03 Mar '21

03 Mar '21

Dear All, A gentle reminder for today's seminar by Prof. Liang Huang from Oregon State University. He will be presenting *"*COVID-19 Vaccine Design using Mathematical Linguistics*"* between* 1.00-2.00PM PT.* Zoom Link: https://tinyurl.com/arhbuvs3 Please find attached the poster flyer for more information. *Title*: COVID-19 Vaccine Design using Mathematical Linguistics *Abstract*: To defeat the current COVID-19 pandemic, a messenger RNA (mRNA) vaccine has emerged as a promising approach thanks to its rapid and scalable production and non-infectious and non-integrating properties. However, designing an mRNA sequence to achieve high stability and protein yield remains a challenging problem due to the exponentially large search space (e.g., there are 2.4 x 10^632 possible mRNA sequence candidates for the spike protein of SARS-CoV-2). We describe two on-going efforts for this problem, both using linear-time algorithms inspired by my earlier work in natural language parsing. On one hand, the Eterna OpenVaccine project from Stanford Medical School takes a crowd-sourcing approach to let game players all over the world design stable sequences. To evaluate sequence stability (in terms of free energy), they use LinearFold from my group (2019) since it’s the only linear-time RNA folding algorithm available (which makes it the only one fast enough for COVID-scale genomes). On the other hand, we take a computational approach to directly search for the optimal sequence in this exponentially large space via dynamic programming. It turns out this problem can be reduced to a classical problem in formal language theory and computational linguistics (intersection between CFG and DFA), which can be solved in O(n^3) time, just like lattice parsing for speech. In the end, we can design the optimal mRNA vaccine candidate for SARS-CoV-2 spike protein in just about 10 minutes. To conclude, classical results (dating back to the 1960s) from theoretical computer science and mathematical linguistics helped us solve the very challenging and extremely important problem in fighting the COVID-19 pandemic. *Bio*: Liang Huang (PhD, Penn, 2008) is an Associate Professor of Computer Science at Oregon State University and a Distinguished Scientist at Baidu Research USA. He is a leading theoretical computational linguist, and was recognized at ACL 2008 (Best Paper Award) and ACL 2019 (Keynote Speech), but in recent years he has been more interested in applying his expertise in parsing, translation, and grammar formalisms to biology problems such as RNA folding and RNA design. Since the outbreak of COVID-19, he has shifted his attention to the fight against the virus, which resulted in efficient algorithms for stable mRNA vaccine design, adapted from classical theory and algorithms from mathematical linguistics dating back to the 1960s. Please plan on attending! Thanks, Jay Patravali Graduate Student, CoRIS-EECS. Oregon State University ---- AI Seminar Important Reminders: -> The AI Seminar has a strict "no electronics" and "no recordings" policy. -> For graduate students in the AI program, attendance is strongly encouraged.

1 0

Fwd: ROB 562: Human Control Systems class in Spring 2021
by Patravali, Jay Sanjay 01 Mar '21

01 Mar '21

Dear all, Prof Ravi Balasubramanian is teaching. ROB 562: Human Control Systems" in Spring 2021. Please see the message below. Thanks, Jay ---------- Forwarded message --------- From: Balasubramanian, Ravi <Ravi.Balasubramanian(a)oregonstate.edu> Date: Fri, Feb 26, 2021 at 5:59 PM Subject: ROB 562: Human Control Systems class in Spring 2021 To: Patravali, Jay Sanjay <patravaj(a)oregonstate.edu> Hi Jay: I am an OSU robotics faculty. Can you please forward the below message and the attachment to the AI list about a course that is upcoming in Spring? Thanks! Ravi -------------------------- Friends: Hope your term is going great. I wanted to inform you that I will teach a course titled "ROB 562: Human Control Systems" in Spring 2021. The flyer is attached. The material may be relevant to your students, and more generally, to students interested in the following: neuro-musculo-skeletal system biomechanics bio-control biosignals feedback control for biomechanical systems models for human-robot communication for physical interaction bioengineering prostheses, exoskeletons, orthoses application of machine learning and AI to the above domains Please advertise this course when you get a chance. We look forward to having a diverse group in the class. :) Thanks! -- Ravi Balasubramanian Associate Professor School of Mechanical, Industrial, and Manufacturing Engineering Oregon State University Corvallis, OR 97331. ravi.balasubramanian(a)oregonstate.edu Graf Hall 315 Ph#: 541-737-4267 http://web.engr.oregonstate.edu/~balasubr/ Public calendar: http://bit.ly/1a4YXpD OSU Robotics: http://robotics.oregonstate.edu/

1 0

[CoRIS-List] Seminar *Today* 10am: Joseph Foley, Axiomatic Design for Robotics
by Ross Hatton 26 Feb '21

26 Feb '21

Hi All, As a reminder, our seminar today will be "Axiomatic Design for Robotics", by Dr. Joseph T. Foley of Reykjavik University. Seminar time: 10am PST, Friday February 26 Seminar zoom link: https://oregonstate.zoom.us/j/97644079157?pwd=WXRZeEhOR0padXVzb2NkVkVkVEFmZ… <https://oregonstate.zoom.us/j/97644079157?pwd=WXRZeEhOR0padXVzb2NkVkVkVEFmZ…> Seminar slides: https://www.overleaf.com/read/xhtggvxwyymf <https://www.overleaf.com/read/xhtggvxwyymf> -Ross --------------------- Abstract: Dr. Joseph T. Foley has been thinking about design and how it can be incorporated into the multidisciplinary study of robotics and mechatronics. The field is inherently challenging for students to gain mastery of due to the need for competence in the disciplines of software, electronics, and mechanical engineering. In this presentation, he will give a quick tutorial on Axiomatic Design, explain some of the research he is performing with it, and showcase past student projects. Biography: Dr. Joseph Timothy Foley (MIT BSc ‘99, MEng, ‘99, PhD ‘07) has worked as a researcher and designer in a large variety of fields with a heavy emphasis on infrastructure and mechatronics. His graduate research at MIT focused on integrating RFID into smart devices in a scalable and secure way, and he holds patents on the Object Name System for linking RFID-tagged objects to the responsible party. After completing his PhD, Dr. Foley worked as a researcher in the Environmentally Benign Manufacturing group at MIT in partnership with SKF, investigating methods of reducing the impact and energy usage of manufacturing processes. At iRobot's Government and Industrial division, he developed shape-changing robots as the technical lead for the Harvard-MIT-iRobot DARPA ChemBots team; this research resulted in a US patent on the manufacture of enhanced Shape Memory Alloy springs for soft robotics. Dr. Foley is now an assistant professor at Reykjavik University and teaches topics in mechatronics and mechanical design. He has integrated Axiomatic Design into the courses he currently teaches to provide students with a common framework for the heavily multi-disciplinary nature of modern computer-controlled manufacturing and smart devices. His research interests include product design, embedded smart devices and IoT, wireless communication, physical security, and engineering-artist collaborations. Dr. Foley's work-related hobbies include developing interactive installations for Icelandic art museums. His most recent developments in Axiomatic Design research include Creative Axiomatic Design (CIRP DC 2016), Desirable Complexity (ICAD 2017), and Axiomatic Design as an Ontology (CIRP DC 2017). He is the co-editor for "Design Engineering and Science", a Springer Nature educational textbook which intends to make Axiomatic Design accessible to a large range of fields and teaching styles. Dr. Foley's web site: https://afs.cs.ru.is/user/f/foley/www/ <https://afs.cs.ru.is/user/f/foley/www/> =========== Ross L. Hatton Associate Professor, Robotics and Mechanical Engineering Collaborative Robotics and Intelligent Systems Institute (CoRIS) Oregon State University coris.oregonstate.edu <http://coris.oregonstate.edu/> research.engr.oregonstate.edu/lram/ rosslhatton.com ross.hatton(a)oregonstate.edu

1 0

OSU AI Seminar - March 3 2021 | Liang Huang, Oregon State University
by Patravali, Jay Sanjay 25 Feb '21

25 Feb '21

Dear All, Our next speaker is Prof. Liang Huang from Oregon State University. He will be presenting *"*COVID-19 Vaccine Design using Mathematical Linguistics*"* on *Wednesday 3/3 from 1.00-2.00PM PT.* Zoom Link: https://tinyurl.com/arhbuvs3 Please find attached the poster flyer for more information. *Title*: COVID-19 Vaccine Design using Mathematical Linguistics *Abstract*: To defeat the current COVID-19 pandemic, a messenger RNA (mRNA) vaccine has emerged as a promising approach thanks to its rapid and scalable production and non-infectious and non-integrating properties. However, designing an mRNA sequence to achieve high stability and protein yield remains a challenging problem due to the exponentially large search space (e.g., there are 2.4 x 10^632 possible mRNA sequence candidates for the spike protein of SARS-CoV-2). We describe two on-going efforts for this problem, both using linear-time algorithms inspired by my earlier work in natural language parsing. On one hand, the Eterna OpenVaccine project from Stanford Medical School takes a crowd-sourcing approach to let game players all over the world design stable sequences. To evaluate sequence stability (in terms of free energy), they use LinearFold from my group (2019) since it’s the only linear-time RNA folding algorithm available (which makes it the only one fast enough for COVID-scale genomes). On the other hand, we take a computational approach to directly search for the optimal sequence in this exponentially large space via dynamic programming. It turns out this problem can be reduced to a classical problem in formal language theory and computational linguistics (intersection between CFG and DFA), which can be solved in O(n^3) time, just like lattice parsing for speech. In the end, we can design the optimal mRNA vaccine candidate for SARS-CoV-2 spike protein in just about 10 minutes. To conclude, classical results (dating back to the 1960s) from theoretical computer science and mathematical linguistics helped us solve the very challenging and extremely important problem in fighting the COVID-19 pandemic. *Bio*: Liang Huang (PhD, Penn, 2008) is an Associate Professor of Computer Science at Oregon State University and a Distinguished Scientist at Baidu Research USA. He is a leading theoretical computational linguist, and was recognized at ACL 2008 (Best Paper Award) and ACL 2019 (Keynote Speech), but in recent years he has been more interested in applying his expertise in parsing, translation, and grammar formalisms to biology problems such as RNA folding and RNA design. Since the outbreak of COVID-19, he has shifted his attention to the fight against the virus, which resulted in efficient algorithms for stable mRNA vaccine design, adapted from classical theory and algorithms from mathematical linguistics dating back to the 1960s. Please plan on attending! Thanks, Jay Patravali Graduate Student, CoRIS-EECS. Oregon State University ---- AI Seminar Important Reminders: -> The AI Seminar has a strict "no electronics" and "no recordings" policy. -> For graduate students in the AI program, attendance is strongly encouraged.

1 0

[CoRIS-List] Seminar Feb 26: Joseph Foley, Axiomatic Design for Robotics
by Ross Hatton 24 Feb '21

24 Feb '21

Hi All, As a reminder, our seminar this week will be "Axiomatic Design for Robotics", by Dr. Joseph T. Foley of Reykjavik University. Seminar time: 10am PST, Friday February 26 Seminar zoom link: https://oregonstate.zoom.us/j/97644079157?pwd=WXRZeEhOR0padXVzb2NkVkVkVEFmZ… <https://oregonstate.zoom.us/j/97644079157?pwd=WXRZeEhOR0padXVzb2NkVkVkVEFmZ…> -Ross --------------------- Abstract: Dr. Joseph T. Foley has been thinking about design and how it can be incorporated into the multidisciplinary study of robotics and mechatronics. The field is inherently challenging for students to gain mastery of due to the need for competence in the disciplines of software, electronics, and mechanical engineering. In this presentation, he will give a quick tutorial on Axiomatic Design, explain some of the research he is performing with it, and showcase past student projects. Biography: Dr. Joseph Timothy Foley (MIT BSc ‘99, MEng, ‘99, PhD ‘07) has worked as a researcher and designer in a large variety of fields with a heavy emphasis on infrastructure and mechatronics. His graduate research at MIT focused on integrating RFID into smart devices in a scalable and secure way, and he holds patents on the Object Name System for linking RFID-tagged objects to the responsible party. After completing his PhD, Dr. Foley worked as a researcher in the Environmentally Benign Manufacturing group at MIT in partnership with SKF, investigating methods of reducing the impact and energy usage of manufacturing processes. At iRobot's Government and Industrial division, he developed shape-changing robots as the technical lead for the Harvard-MIT-iRobot DARPA ChemBots team; this research resulted in a US patent on the manufacture of enhanced Shape Memory Alloy springs for soft robotics. Dr. Foley is now an assistant professor at Reykjavik University and teaches topics in mechatronics and mechanical design. He has integrated Axiomatic Design into the courses he currently teaches to provide students with a common framework for the heavily multi-disciplinary nature of modern computer-controlled manufacturing and smart devices. His research interests include product design, embedded smart devices and IoT, wireless communication, physical security, and engineering-artist collaborations. Dr. Foley's work-related hobbies include developing interactive installations for Icelandic art museums. His most recent developments in Axiomatic Design research include Creative Axiomatic Design (CIRP DC 2016), Desirable Complexity (ICAD 2017), and Axiomatic Design as an Ontology (CIRP DC 2017). He is the co-editor for "Design Engineering and Science", a Springer Nature educational textbook which intends to make Axiomatic Design accessible to a large range of fields and teaching styles. Dr. Foley's web site: https://afs.cs.ru.is/user/f/foley/www/ =========== Ross L. Hatton Associate Professor, Robotics and Mechanical Engineering Collaborative Robotics and Intelligent Systems Institute (CoRIS) Oregon State University coris.oregonstate.edu research.engr.oregonstate.edu/lram/ rosslhatton.com ross.hatton(a)oregonstate.edu

1 0