| Title: |
Design Automation for Learning-Enabled Cyber-Physical Systems |
|
| Speaker: |
朱祺 副教授，美国西北大学 |
|
| Time: |
5月5日（周五）上午10:00 |
|
| Venue: |
线上：腾讯会议号：870-273-428 |
|
|
| Abstract: |
Future learning-enabled cyber-physical systems (LE-CPSs), such as self-driving cars and robotic systems, will employ complex machine learning-based sensing, computation and communication components for their perception, prediction, planning, control, and coordination. However, ensuring their safety, robustness and security faces tremendous challenges, given the highly dynamic and uncertain environment they operate within, the fast increase of their functional and architectural complexity, the difficulty in analyzing deep neural network-based components, and the often-stringent resource and timing constraints. This calls for new design automation methodologies and tools that support rigorous, accurate and efficient modeling, synthesis, verification, and adaptation of LE-CPSs. In this talk, using connected and autonomous vehicles (CAVs) as an example, I will discuss these challenges and present some of our recent work to address them in a holistic manner, including 1) end-to-end verification, design and adaptation methods for ensuring robust and safe application of neural networks in perception and decision making; and 2) cross-layer methods based on weakly-hard paradigm for mitigating execution disturbances (e.g., timing violations, soft errors, malicious attacks). |
|
| Bio: |
Qi Zhu is an Associate Professor at the ECE Department in Northwestern University. He received a Ph.D. in EECS from University of California, Berkeley in 2008, and a B.E. in CS from Tsinghua University in 2003. His research interests include design automation for cyber-physical systems (CPS) and Internet of Things, safe and secure machine learning for CPS and IoT, cyber-physical security, and system-on-chip design, with applications in domains such as connected and autonomous vehicles, energy-efficient smart buildings, and robotic systems. He is a recipient of the NSF CAREER award, the IEEE TCCPS Early-Career Award, and the Humboldt Research Fellowship for Experienced Researchers. He received best paper awards at DAC 2006, DAC 2007, ICCPS 2013, ACM TODAES 2016, and DATE 2022. He is the Conference Chair of IEEE TCCPS, and VP of Young Professionals at IEEE CEDA. He is an Associate Editor for IEEE TCAD, ACM TCPS, and IET Cyber-Physical Systems: Theory & Applications, and has served as a Guest Editor for the Proceedings of the IEEE, ACM TCPS, IEEE T-ASE, Elsevier JSA, and Elsevier Integration, the VLSI journal. |
|
