Yanbing Mao | Ph.D.
 |
Assistant Professor |
Opening
My research group has several Ph.D. positions fully funded by a project on safe Physics-AI, see the [AD].
Research Interests
Safe Physics‐AI
Dynamics and Control of Social Information
Application Domains
Self-Driving Vehicles
Quadruped Robots
Social Cybersecurity
Work Experience
Assistant Professor, Wayne State University, Aug. 2022 – Present
Postdoctoral Research Associate, University of Illinois at Urbana-Champaign, Oct. 2019 – Jul. 2022
Education
Ph.D. in Electrical and Computer Engineering, State University of New York at Binghamton, Sept. 2015 – Sept. 2019
M.E. in Circuits & Systems, University of Electronic Science and Technology of China, Sept. 2010 – Jul. 2013
News
[05-25-2024] Our Physics-AI team proposed the SeC-Learning Machine: Simplex-enabled safe continual learning machine. The learning machine will ensure the lifetime safety of learning in real plants and real environments using real-time data. Thus, the SeC-learning machine can address the Sim2Real gap and learn to tolerate unknown unknowns. The demo video is available at "SeC-Learning Machine’’. The source code and paper will be open soon.
[03-15-2024] We have opened the "Phy-DRL’’, including source codes and demo videos.
[01-16-2024] Our Physics-AI work "Phy-DRL: Physics-Regulated Deep Reinforcement Learning: Invariant Embeddings’’ got accepted at ICLR 2024 as a spotlight (5%)! Phy-DRL features 1) automatic construction of safety-embedded reward, given many safety conditions or regulations, 2) mathematically-provable safety guarantee, and 3) fast training towards safety guarantee. The theoretical claims were demonstrated by training a quadruped robot and a cart-pole system.
[12-15-2023] Our Physics-AI work "Phy-Taylor: Partially Physics-Knowledge-Enhanced Deep Neural Networks via NN Editing’’ is accepted by IEEE Transactions on Neural Networks and Learning Systems!
[07-15-2023] Our Physics-AI work "Physics-Model-Regulated Deep Reinforcement Learning Towards Safety & Stability Guarantees’’ is accepted by 62nd IEEE Conference on Decision and Control!
[12-14-2022] Our paper "Social System Inference from Noisy Observations’’ is accepted by IEEE Transactions on Computational Social Systems!
[11-04-2022] Our paper "Cost Function Learning in Memorized Social Networks with Cognitive Behavioral Asymmetry’’ is accepted by IEEE Transactions on Computational Social Systems!
[09-15-2022] Our paper "SL1-Simplex: Safe Velocity Regulation of Self-Driving Vehicles in Dynamic and Unforeseen Environments’’ is accepted by ACM Transactions on Cyber-Physical Systems (Special Issue on Automotive CPS Safety & Security)!
[09-01-2022] Latest Demo of safe and fast driving of self-driving car is available: ‘‘Youtube’’. The car is controlled by our proposed self-correcting physics-AI, named, Phy-Taylor.
[02-15-2022] I am co-organizing the 7th International Workshop on Social Sensing, an ICWSM 2022 full-day workshop. The submission deadline is March 27, 2022. Please consider submitting your full papers and/or vision abstracts to the workshop. ‘‘2022 ICWSM–Social Sensing’’. Detailed information can be found at ‘‘Belief Dynamics’’.
[01-25-2022] Latest Demo of safe driving of self-driving vehicles in the dynamic and unforeseen environemnts is available: ‘‘Youtube’’.
[07-09-2021] Open source codes of safe velocity regulation of self-driving vehicles are available at ‘‘GitHub: AutoRally-Safe Velocity Regulation’’.
[07-05-2021] Demos of safe velocity regulation of self-driving vehicles in the dynamic and unforeseen environemnts are available: ‘‘Model Learning based RHAC v.s. RHAC’’, ‘‘L1 Adaptive Controller v.s. Normal Controller’’.
[06-03-2021] I gave a talk of ‘‘Apollo-Rokwire: Infodemics Management Framework’’ in the workshop ‘‘Rethinking Socio-Cyber-Physical Systems of Tomorrow’’ at 2021 NSF CPS PI meeting.
[12-18-2020] Our paper ‘‘Impact of Confirmation Bias on Competitive Information Spread in Social Networks’’ is accepted by IEEE Transactions on Control of Network Systems!