Adversarial Learning-Based On-Line Anomaly Monitoring for Assured Autonomy
This addresses safety and security issues for autonomous systems like unmanned vehicles, but it is incremental as it builds on existing adversarial and prediction methods.
The paper tackles real-time safety monitoring in learning-based control systems by proposing an on-line framework with two anomaly detection components, demonstrating effectiveness on an autonomous ground vehicle and a public dataset.
The paper proposes an on-line monitoring framework for continuous real-time safety/security in learning-based control systems (specifically application to a unmanned ground vehicle). We monitor validity of mappings from sensor inputs to actuator commands, controller-focused anomaly detection (CFAM), and from actuator commands to sensor inputs, system-focused anomaly detection (SFAM). CFAM is an image conditioned energy based generative adversarial network (EBGAN) in which the energy based discriminator distinguishes between proper and anomalous actuator commands. SFAM is based on an action condition video prediction framework to detect anomalies between predicted and observed temporal evolution of sensor data. We demonstrate the effectiveness of the approach on our autonomous ground vehicle for indoor environments and on Udacity dataset for outdoor environments.