← Search

James Sharp

2 accepted papers

2020

Practical Verification of Neural Network Enabled State Estimation System for Robotics

IROS 2020poster

We study for the first time the verification problem on learning-enabled state estimation systems for robotics, which use Bayes filter for localisation, and use deep neural network to process sensory input into observations for the Bayes filter. Specifically, we are interested in a robustness proper…

Cited by 7SourceScholar
2020

Reliability Validation of Learning Enabled Vehicle Tracking

ICRA 2020poster

This paper studies the reliability of a real-world learning-enabled system, which conducts dynamic vehicle tracking based on a high-resolution wide-area motion imagery input. The system consists of multiple neural network components - to process the imagery inputs - and multiple symbolic (Kalman fil…

Cited by 13SourceScholar