The AIAA Intelligent Systems Technical Committee (ISTC) is concerned with the application of Intelligent System (IS) technologies and methods to aerospace systems, the verification and validation of these systems, and the education of the AIAA membership in the use of IS technologies in aerospace and other technical disciplines.
Announcements
These are announcements originally posted to the main page.
- Announcements
- News: 2022 December 13, 9:30pm EST (by Cat McGhan)
- News: 2022 October 24, 2:07pm EDT (by Cat McGhan)
- News: 2022 July 12, 8:28pm EST (by Cat McGhan)
- News: 2021 December 20, 9:50pm EST (by Cat McGhan)
- News: 2021 March 6, 2:57pm EST (by Cat McGhan)
- News: 2020 August 19, 9:35pm EST (by Cat McGhan)
- News: 2020 April 29, 12:33pm EST (by Cat McGhan)
- News: 2020 February 28, 3:42pm EST (by Cat McGhan)
- News: 2019 January 08, 4:40pm EST (by Cat McGhan)
- News: 2018 September 13, 1:39am EST (by Cat McGhan)
- News: 2018 September 13, 1:38am EST (by Cat McGhan)
News: 2022 December 13, 9:30pm EST (by Cat McGhan)
ISTC Technical Seminar Series – Chetan S. Kulkarni, on Zoom
ISTC Technical Seminar Series
Don’t miss Dr. Chetan S. Kulkarni’s seminar on Wednesday at 4:00pm EST on Zoom!
Speaker: Chetan S. Kulkarni, Ph.D.
Staff Researcher, Prognostics Center of Excellence and the Diagnostics and Prognostics Group
Intelligent Systems Division, NASA Ames Research Center
Date/time: Wednesday, December 14th, 2022 – 4:00pm-5:00pm Eastern time
Title: Hybrid Approaches for Systems Health Management and Prognostics
Meeting link: https://aiaa.zoom.us/j/86978612062?pwd=ZFJXTlVJaTE0K1Q0VWNzMVVjTWF6dz09
Dial by your location
877 853 5257 US Toll-free
888 475 4499 US Toll-free
Meeting ID: 869 7861 2062
Passcode: 553359
Abstract: To facilitate and solve the prediction problem, awareness of the current health state of the system is key, since it is necessary to perform condition-based predictions. To accurately predict the future state of any system, it is required to possess knowledge of its current health state and future operational conditions. Latest achievements of data-driven algorithms in regression of complex nonlinear functions and classification tasks have generated a growing interest in artificial intelligence for industrial applications. Complex multi-physics models as well as digital twins, once purely built on physics and corresponding simplified lumped parameter iterations, can now benefit from machine learning algorithms to mitigate the lack of understanding of some complex behavior. Given models of the current and future system behavior, a general approach of model-based prognostics can solve the prediction problem and further decision making. In principle, data driven approaches can replace expensive experimental test-setups as well as reduce the number of simulations needed to explore, e.g., the parametric space of a multi-parameter model. Nonetheless, the limitations of pure data-driven methods came to light rather quickly, at least for some industries. In many industrial applications, data acquisition is costly, and the volume of data that can be collected does not satisfy the requirements for an effective model training and cross-validation. Therefore, some recent works in the area of machine learning is focusing on blending physics with data-driven algorithms, thus mitigating the drawbacks of the two approaches and emphasizing respective advantages. Partial physical knowledge of the problem can aid the learning process by “guiding” the algorithm towards efficient solutions that satisfy the physics driving the system behavior. The result is a hybrid modeling approach combining physical knowledge as well data driven methods to develop a unified hybrid approach. A hybrid framework for fusing information from physics-based performance models along with deep learning algorithms for prognostics of complex safety critical systems is presented. In this framework, physics-based performance models infer unobservable model parameters related to the system’s components health solving a calibration problem in the deep learning approach.
Bio: Chetan S. Kulkarni is a staff researcher at the Prognostics Center of Excellence and the Diagnostics and Prognostics Group in the Intelligent Systems Division at NASA Ames Research Center. His current research interests are in Systems Diagnostics, Prognostics and Health Management. Specifically focused in the area of developing physics-based and hybrid modeling approaches for diagnosis and prognosis of complex systems. He completed his MS (09), Ph.D. (
13) from Vanderbilt University, TN where he was a Graduate Research Assistant with the Institute for Software Integrated Systems and Department of Electrical Engineering and Computer Science. He completed his BE (`02) from the University of Pune, India. Prior to joining Vanderbilt, he was a Research Fellow at the Department of Electrical Engineering, IIT-Bombay, where his research work focused on developing low-cost substation automation system monitoring and control devices and partial discharge of high voltage transformers. Earlier to that he was a member of the technical team of the Power Automation group at Honeywell, India where he was involved in turnkey power automation projects and product development in the area of substation automation. He is KBR Technical Fellow, AIAA Associate Fellow and Associate Editor for IEEE, SAE, IJPHM Journals on topics related to Prognostics and Systems Health Management. He has been Technical Program Committee co-chair at PHME18, PHM20 and PHM21. He co-chairs the Professional Development and Education Outreach subcommittee in the AIAA Intelligent Systems Technical Committee.
News: 2022 October 24, 2:07pm EDT (by Cat McGhan)
ISTC Technical Seminar Series – K. Merve Dogan, on Zoom
ISTC Technical Seminar Series
Don’t miss Dr. K. Merve Dogan’s seminar today at 5:00pm EDT on Zoom!
Speaker: K. Merve Dogan, Ph.D.
Department of Aerospace Engineering; Assistant Professor
Embry-Riddle Aeronautical University, Daytona Beach, Florida, USA
Date/time: Monday, October 24th, 2022 – 5:00pm-6:00pm Eastern time
Title: Verifiable Adaptive Architectures for Control of Safety-Critical Systems
Meeting link: https://aiaa.zoom.us/j/87121537657?pwd=TW82Z05aMWZ2ekRGTXRQRkxrVld4UT09
Dial by your location
877 853 5257 US Toll-free
888 475 4499 US Toll-free
Meeting ID: 871 2153 7657
Passcode: 261822
Abstract: Model reference adaptive control (MRAC) methods are powerful mathematical tools for safety-critical sole and multiagent systems, where they have the capability to suppress the effect of exogenous disturbances and system uncertainties for achieving a desired level of closed-loop system response. However, the closed-loop system stability with these methods can be challenged for a wide array of applications that involve unmodeled dynamics (e.g., rigid body systems coupled with flexible appendages, airplanes with high aspect ratio wings, and high-speed vehicles with rigid body and flexible dynamics coupling) and actuator dynamics (e.g., cooperation of low and high speed autonomous vehicles). Motivated by this standpoint, this seminar will introduce verifiable MRAC architectures for both sole and multiagent systems, where we will show the stability tradeoffs of these architectures in the presence of unmodeled and actuator dynamics as well as system uncertainties. In order to bridge the gap between theory and practice, several simulation and experimental results will be also presented.
Bio: Dr. K. Merve Dogan is an Assistant Professor of the Department of Aerospace Engineering at the Embry-Riddle Aeronautical University and the director of Foundational Autonomous Systems and Technologies Research Group (FAST- https://www.fastresearchgroup.com) since August 2020. Prior to joining the Embry-Riddle Aeronautical University, she held the Research Assistant position in the Department of Mechanical Engineering at the University of South Florida between 2015 and 2020, where she received her Doctor of Philosophy degree in 2020. Before joining the University of South Florida, she held a Research/Teaching Assistant position in the Department of Electrical and Electronics Engineering at the Izmir Institute of Technology between 2012 and 2015, where she received her Master of Science degree in 2016. Dr. Dogan is a Co-Director of the Forum on Robotics and Control Engineering (FoRCE), and is a member of AIAA and IEEE, including several technical committees.
News: 2022 July 12, 8:28pm EST (by Cat McGhan)
Call for Papers – 2nd Workshop on AI for Space in conjunction with ECCV 2022
Call for Papers – 2nd Workshop on AI for Space in conjunction with ECCV 2022:
AI4Space focuses on the role of AI, particularly computer vision and machine learning, in helping to solve technical challenges related to space, from autonomous spacecraft, space mining, debris monitoring and mitigation, to answering fundamental questions about the universe. The workshop will highlight the space capabilities that draw from and/or overlap significantly with vision and learning research, outline the unique difficulties presented by space applications to vision and learning, and discuss recent advances towards overcoming those obstacles.
Website:
https://aiforspace.github.io/2022/
Call for Papers:
We solicit papers for AI4Space. Papers will be reviewed and accepted papers will be published in the proceedings of ECCV Workshops. Authors of accepted papers will also be invited to present at the workshop (in hybrid mode) at ECCV 2022, Tel-Aviv, late October 2022.
The general emphasis of AI4Space is vision and learning algorithms in off-Earth environments, including in the orbital region, surface and underground environments on other planetary bodies (e.g., the moon, Mars and asteroids), interplanetary space and solar system, and distant galaxies. Target application areas include autonomous spacecraft, space robotics, space traffic management, astronomy, astrobiology and cosmology. Emphasis is also placed on novel sensors and processing hardware for vision and learning in space, mitigating the challenges of the space environment towards vision and learning (e.g., solar radiation, extreme temperatures), and solving practical difficulties in vision and learning for space (e.g., lack of training data, unknown or partially known characteristics of operating environments).
A specific list of topics is as follows:
- Visual navigation for spacecraft operations
- Vision and learning for space robotics
- GPS-denied positioning on the moon and Mars
- Space debris monitoring and mitigation
- Vision and learning for astronomy, astrobiology and cosmology
- Novel sensors for space applications
- Processing hardware for vision and learning in space
- Mitigating challenges of the space environment to vision and learning
- Datasets, transfer learning and domain gap for space problems
Paper deadline: 11:59pm 15 July 2022
More details: https://aiforspace.github.io/2022/
News: 2021 December 20, 9:50pm EST (by Cat McGhan)
Jon How’s keynote at SciTech 2022
Jon How’s keynote at SciTech 2022
Don’t miss Prof. Jonathan How’s keynote at SciTech 2022 on January 3rd at 11:30am PST. Professor How will talk about “Deploying Autonomy in an Uncertain World”. More info at https://www.aiaa.org/SciTech/program and below!
Date/time: Monday, January 3rd, 2022 – 11:30 PST
Title: Deploying Autonomy in an Uncertain World
Abstract: As autonomy capabilities have matured, there is growing interest in transitioning algorithms from the laboratory to the field. However, this typically leads to a painful exercise in which prior assumptions end up being violated and algorithms tend to break down, leading to poor performance in the real-world. The types of challenges faced in the real-world include disturbances (e.g., wind gusts) and modeling errors, imperfect communication networks, and the limited capabilities of onboard perception systems. This talk will describe recent advances in accounting for these types of real-world uncertainties in autonomy algorithms. To handle disturbances, I will describe a new learning approach that uses Robust Tube MPC during training to augment an expert’s training set, which is shown to enable a multirotor to learn to fly through turbulence from only a few demonstrations collected without any disturbances acting on the vehicle. To support distributed autonomy and estimation with limited communication resources, I will discuss developing censoring rules and learned communication policies to enable agents to determine if communicating for a specific navigation or planning task is justified given the message importance and network congestion. To account for the constraints of onboard perception systems (e.g., limited range and field-of-view, and corrupted by noise) I will highlight recent work on targetless multi-sensor calibration and perception-aware motion planning. Finally, the talk will motivate and outline methods for certifying the safety and performance properties of learning-based approaches, which requires ensuring that the uncertainty in the understanding of the real world is appropriately captured in the models used by the autonomous systems.
Bio: Jonathan P. How is the Richard C. Maclaurin Professor of Aeronautics and Astronautics at the Massachusetts Institute of Technology. He received a B.A.Sc. (aerospace) from the University of Toronto in 1987, and his S.M. and Ph.D. in Aeronautics and Astronautics from MIT in 1990 and 1993, respectively, and then studied for 1.5 years at MIT as a postdoctoral associate. Prior to joining MIT in 2000, he was an assistant professor in the Department of Aeronautics and Astronautics at Stanford University.
Dr. How was the editor-in-chief of the IEEE Control Systems Magazine (2015-19) and is an associate editor for the AIAA Journal of Aerospace Information Systems and the IEEE Transactions on Neural Networks and Learning Systems. He was an area chair for International Joint Conference on Artificial Intelligence (2019) and will be the program vice-chair (tutorials) for the Conference on Decision and Control (2021). He was elected to the Board of Governors of the IEEE Control System Society (CSS) in 2019 and is a member of the IEEE CSS Technical Committee on Aerospace Control and the Technical Committee on Intelligent Control. He is the Director of the Ford-MIT Alliance and was a member of the USAF Scientific Advisory Board (SAB) from 2014-17.
His research focuses on robust planning and learning under uncertainty with an emphasis on multiagent systems, and he was the planning and control lead for the MIT DARPA Urban Challenge team. His work has been recognized with multiple awards, including the 2020 IEEE CSS Distinguished Member Award, the 2020 AIAA Intelligent Systems Award, the 2015 AeroLion Technologies Outstanding Paper Award for Unmanned Systems, the 2015 IEEE CSS Video Clip Contest, the 2011 IFAC Automatica award for best applications paper, and the 2002 Institute of Navigation Burka Award. He also received the Air Force Commander’s Public Service Award in 2017. He is a Fellow of IEEE and AIAA and was elected to the National Academy of Engineering in 2021.
News: 2021 March 6, 2:57pm EST (by Cat McGhan)
1st Workshop on AI for Space in conjunction with CVPR 2021: June 2021
1st Workshop on AI for Space in conjunction with CVPR 2021: June 2021
AI4Space focuses on the role of AI, particularly computer vision and machine learning, in helping to solve technical challenges related to space, from autonomous spacecrafts, space mining, debris monitoring and mitigation, to answering fundamental questions about the universe. The workshop will highlight the space capabilities that draw from and/or overlap significantly with vision and learning research, outline the unique difficulties presented by space applications to vision and learning, and discuss recent advances towards overcoming those obstacles.
Website: https://aiforspace.github.io/2021/
Featuring keynotes by:
- Shirley Ho (Flatiron Institute), Deep learning for cosmology
- Courtney Mario (Draper Lab), Vision for precision landing and sample return
- Dario Izzo (ESA), AI for spacecraft guidance, dynamics and control
- Yang Gao (Surrey Space), Space autonomous systems
Call for papers on:
- Visual navigation for spacecraft operations
- Vision and learning for space robotics
- Positioning, mapping and SLAM for the moon and Mars
- Autonomous celestial positioning
- Space debris monitoring and mitigation
- Vision and learning for astronomy, astrobiology and cosmology
- Sensors for space applications
- AI and learning-based satellite communications and IoT
- Processing hardware for vision and learning in space, including satellite on-board processing
- Mitigating challenges of the space environment to vision and learning
- Datasets, transfer learning and domain gap for space problems
Paper deadline: extended to 11:59pm 20 Mar 2021 (PST)
Submission details: https://aiforspace.github.io/2021/#cfp
News: 2020 August 19, 9:35pm EST (by Cat McGhan)
Two of our TC members were featured in a news article recently!
Two of our TC members were featured in a news article recently!
Analysis: Sanitization Drones Could Improve Campus Safety
EDTECH Magazine (8/10, Stone) reports that “at the University of Michigan, Aerospace Engineering Professor Ella Atkins envisions a school using UAVs to clean learning spaces.” Said Atkins, “If the drone can pop up above the tables and chairs and spray a fast-drying solution, just zipping back and forth in a regular pattern, there’s no way a human could do that nearly as fast. That has real possibilities.” A small drone “likely couldn’t carry enough cleaning fluid to get the job done,” but “running a lightweight hose from the drone back to a bucket of solution introduces challenges.” Said Kelly Cohen, interim head of the Department of Aerospace Engineering and Engineering Mechanics at the University of Cincinnati, “There are spaces where you have a lot of students congregating, maybe moving from one building to another, and that open space could be disinfected by drones.”
News: 2020 April 29, 12:33pm EST (by Cat McGhan)
2020 IS Workshop has been POSTPONED
The 2020 IS Workshop has been POSTPONED UNTIL SUMMER 2021. We thank you for your patience and forbearance in these COVID-19 times. You can learn more about the virus and stay up to date on the situation and safety measures to deal with it at the WHO website (or the CDC website for more USA-specific information). In the meantime, please practice social distancing and best practices under these evolving circumstances, and we all hope you stay safe and well. We will all get through this together.
News: 2020 February 28, 3:42pm EST (by Cat McGhan)
2020 IS Workshop Call for abstracts
The call for abstracts for the student talks and poster competition for the 2020 IS Workshop has now been posted.
Pdf flyer is available here!
News: 2019 January 08, 4:40pm EST (by Cat McGhan)
2018 IS Workshop presentation links are online
Presentations from the 2018 IS Workshop are online and available at this location.
The 2019 IS Workshop page is also online! View it at: https://istcws2019.org/
News: 2018 September 13, 1:39am EST (by Cat McGhan)
2018 IS Workshop presentation links coming soon!
Links to the presentations from the 2018 IS Workshop will be made available at this website domain later today. Stay tuned!
News: 2018 September 13, 1:38am EST (by Cat McGhan)
AIAA Sharepoint site issues
The AIAA Sharepoint site seems to have been having issues for a couple of weeks now. Not sure what’s going on, but it’s sped up our move to another webhost for public dissemination of ISTC-related information.
If you want to see the old site as of January 2, 2018 (prior to recent updates), you can visit it via the Internet Archive’s Wayback Machine at this location.