ANN ARBOR, MI
In 2023, TRINA’s work in verification and control for autonomous systems has been prominently featured in top Cyber-Physical Systems and Robotics conferences such as ICRA, ACC, HSCC, and ICCPS, with six papers accepted. Our papers are complementary to publications of other research units in Toyota, tackling challenges that range from robot learning for navigation, risk-aware control, optimization, and verification methods for Deep Neural Networks.
Safety Verification of Deep Neural Networks for Input-Output Specifications [3]: Examining the Relationship Between Falsifying Outputs (Right Subfigure, Red Region) and Corresponding Inputs (Left Subfigure).
Accepted Papers:
- A Neurosymbolic Approach to the Verification of Temporal Logic Properties of Learning enabled Control Systems [ICCPS]
Navid Hashemi, Bardh Hoxha, Tomoya Yamaguchi, Danil Prokhorov, Georgios Fainekos, Jyotirmoy Deshmukh - Safety Under Uncertainty: Tight Bounds with Risk-Aware Control Barrier Functions [ICRA]
Mitchell Black, Georgios Fainekos, Bardh Hoxha, Danil Prokhorov, Dimitra Panagou - Verification of Recurrent Neural Networks with Star Reachability [HSCC]
Hoang-Dung Tran, Sungwoo Choi, Xiaodong Yang, Tomoya Yamaguchi, Bardh Hoxha, Danil Prokhorov - Quantitative Verification for Neural Networks using ProbStars [HSCC]
Hoang-Dung Tran, Sungwoo Choi, Hideki Okamoto, Bardh Hoxha, Georgios Fainekos, Danil Prokhorov - Risk-Awareness in Learning Neural Controllers for Temporal Logic Objectives [ACC]
Navid Hashemi, Xin Qin, Jyotirmoy V Deshmukh, Georgios Fainekos, Bardh Hoxha, Danil Prokhorov, Tomoya Yamaguchi - Stealthy attacks formalized as STL formulas for Falsification of CPS Security [HSCC]
Aniruddh Chandratre,Tomas Hernandez Acosta,Tanmay Khandait, Giulia Pedrielli, Georgios Fainekos