(This presentation is open to all, including non-members. Images by pixabay and Alec Favale at Pexels.com and Unsplash.com)
Special Semi-Hybrid presentation by Dr. Raman of Honeywell and the INCOSE AI Working Group.
Reinforcement Learning for Behavior Evolution in Complex System-of-Systems
Please join us on Wednesday, March 22nd starting at 5:45 pm for a special Semi-Hybrid presentation on complex system of systems (SOS). Dr. Ramakrishnan Raman will present externally, and the presentation will be available both virtually for remote attendees and IN-PERSON for all attendees at Filippi’s Restaurant on large screen TV. There is also a FREE BUFFET for all in-person attendees!
Date: Wednesday, 22 March, 2023, from 5:45 – 7pm Pacific Time
Location: Filippis Restaurant in Kearny Mesa, 5353 Kearny Villa Rd, San Diego, CA 92123 (Google Maps)
Cost: Free. This event also includes a FREE buffet dinner (Italian food, to include pizza, spaghetti, salads) for in-person attendees! Please also invite friends and coworkers who might also be interested in joining INCOSE and our San Diego chapter. RSVP
Zoom link: https://incose-org.zoom.us/j/83999783217
+1 669 900 6833 US
Meeting ID: 839 9978 3217
(Images by Isi Martinez and Spacex at Unsplash.com)
Abstract: Advances in technology have made it easy to integrate multiple modern systems to form complex system-of-systems (SoS) to achieve unparalleled levels of functionality that are otherwise not achievable by the constituent systems in isolation. However the characteristic emergent behaviors of complex SoS — that directly impact its Measures of Effectiveness (MOEs) — is very difficult, if not impossible, to manually explore, anticipate, and arbitrate just from knowledge of its underlying systems. This presentation discusses how Reinforcement Learning can be leveraged to inculcate adaptable intelligence in constituent systems to adapt their behaviors in tandem with the evolution of emergent behavior at the SoS level. The approach involves inculcating an Intelligent-Behavior Evolution Agent, with the necessary constraints to learn to maximize the SoS and system-level MOEs, while adapting itself to the behavior evolution in SoS. The approach is illustrated through case studies pertaining to power grid SoS and heterogeneous UAV swarms.
Speaker: Dr. Ramakrishnan Raman received B. Tech and MS degrees from IIT Madras, and Ph.D. from IIIT-Bangalore. He is currently Fellow at Honeywell Aerospace. He is a certified Six Sigma Black Belt and is INCOSE Certified Expert Systems Engineering Professional – ESEP, and an IEEE Distinguished Lecturer. He has to his credit several publications in refereed international conferences & journals on complex systems architecture design and Artificial Intelligence – Machine Learning and has also received best paper awards. He is active in the professional societies, including IEEE, INCOSE and SAE. In the year 2016, he received the INCOSE Outstanding Service Award. He has also been the Technical Program Chair for international conferences including 2016 & 2019 Asia Oceania Systems Engineering Conference, 2022 SAE AeroCON conference and the 31st INCOSE International Symposium. He has served as Assistant Director for INCOSE Asia Oceania sector for six years, and is currently Co-Chair of INCOSE AI Systems Working Group.