Assuring City Scale Infrastructure Systems


Principal Investigators: Yair Amir, JHU Computer Science and Tamim Sookoor, JHU Applied Physics Lab

Contributors

Overview

AI systems are optimized for the average case. They cannot be used in critical systems that need to guarantee safety in worst case scenarios. The problem with AI systems is the long tail of edge cases that lead to failure situations. We want to gain the benefits of AI on the average case without incurring failures due to the long tail edge cases.

Proposed Approach

Designing a monitoring architecture that can take over from the AI with a safe controller when the AI system is at risk of breaching the system invariants. We intend to combine an invariant-based Black-Box Monitor with a White-Box Monitor that evaluates the confidence of the machine learning algorithm

Flagship Projects

Two ecosystem testbeds targeted at transportation and public safety domains

Presentations



Traffic Simulator Testbed Videos

Safe Controller

Average waiting time is 9.97 seconds

 

RL Model

50K training steps, average waiting time is 34.51 seconds

 

1M training steps, average waiting time is 14.52 seconds

 

3M training steps, average waiting time is 5.58 seconds

 

30M training steps, average waiting time is 0.29 second

 

Moving from grid to real world map

Distributed Systems and Networks Lab
Computer Science Department, Johns Hopkins University
207 Malone Hall
3400 North Charles Street
Baltimore, MD 21218
TEL: (410) 516-5562