BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260730T152637Z
LOCATION:
DTSTART;TZID=America/Los_Angeles:20260728T123600
DTEND;TZID=America/Los_Angeles:20260728T123700
UID:dac_DAC 2026_sess315_RESEARCH720@linklings.com
SUMMARY:Provably Probabilistic Safe Controller Synthesis for Vision-Based 
 Neural Network Control Systems
DESCRIPTION:Qianlong Hu, Hanrui Zhao, and Liqian Chen (National University
  of Defense Technology); Zhengfeng Yang (East China Normal University); an
 d Banghu Yin and Ji Wang (National University of Defense Technology)\n\nTh
 e prevalence of nonlinear systems in safety-critical domains calls for con
 trollers with safety guarantees, while vision-based control relies on high
 -dimensional images complicates both decision-making and formal safety ana
 lysis under uncertainty. This paper proposes a provably safe controller sy
 nthesis method for vision-based neural network control systems. We first e
 mploy a conditional generative adversarial network (cGAN) to approximate t
 he mapping from system states to visual observations and combine it with R
 L-based pretraining to build a verifiable closed-loop structure. A data-dr
 iven model quantifies uncertainties from environmental perturbations, whil
 e martingale theory guides the learning of a stochastic barrier certificat
 e (SBC) to provide rigorous probabilistic safety bounds. Furthermore, coun
 terexamples from verification are used to alternately refine both the cont
 roller and certificate networks, ultimately yielding a controller with for
 mally provable probabilistic safety guarantees. Experimental results on wi
 dely studied benchmarks demonstrate the efficiency and effectiveness of ou
 r approach.\n\nTopics: Quantum\n\nTrack: DES6. Quantum Computing, Systems\
 n\nSession Chairs: Hokeun Kim (Arizona State University); BaekGyu Kim (Dae
 gu Gyeongbuk Institute of Science and Technology); Xiang Chen (Peking Univ
 ersity); Sangyeob Kim (Yonsei University); Robert M. Radway (University of
  Pennsylvania); Prashanth Mohan (University of Pittsburgh); Xiaoxuan Yang 
 (University of Virginia, Stanford University); Ramtin Zand (University of 
 South Carolina); Hadi Kamali (University of Central Florida); Jiafeng Xie 
 (Villanova University); Prabuddha Chakraborty (University of Maine); Junic
 hiro Kadomoto (University of Tokyo); and Yosuke Ueno (RIKEN)\n\n
END:VEVENT
END:VCALENDAR