RUNTIME MODEL VALIDATION FOR PARTIALLY-OBSERVABLE HYBRID SYSTEMS

Patent №

US 11,204,838

Granted

2021-12-21

Filed 2019

Owner

CARNEGIE MELLON UNIVERSITY

AI components

4

ml · kr · planning · hardware

Assignment

Recorded

Dataset

AIPD

2023_r1 edition

Application

16685099

Disclosed herein are techniques to make the synthesized monitoring conditions of partially-observable hybrid systems robust to partial observability of sensor uncertainty and partial controllability due to actuator disturbance. The approach herein shows that the monitoring conditions result in provable safety guarantees with fallback controllers that react to monitor violation at runtime.

Machine learningKnowledge representationPlanningAI hardwareG06F 11/1415G06F 30/15G05B 19/0428G05B 23/0245G05B 23/0286G06F 11/3409G06F 30/20G06F 30/27+4 more

AI classification

Planning1.00
AI hardware1.00
Machine learning0.92
Knowledge representation0.52
Evolutionary computation0.41
Natural language0.00
Speech0.00
Vision0.00

Ownership

CARNEGIE MELLON UNIVERSITY

assignment · 539470405

© 2026 NYSGPT2525 LLC