Embedded out-of-distribution detection on an autonomous robot platform
This addresses safety concerns for autonomous robots by enabling real-time detection of novel data, though it is incremental as it applies existing OOD detection methods to a specific embedded platform.
The paper tackled the problem of unreliable machine learning outputs in safety-critical systems by implementing an unsupervised deep neural network-based out-of-distribution detector on an autonomous robot, achieving an 87.5% success rate in emergency stopping on a designed test bed.
Machine learning (ML) is actively finding its way into modern cyber-physical systems (CPS), many of which are safety-critical real-time systems. It is well known that ML outputs are not reliable when testing data are novel with regards to model training and validation data, i.e., out-of-distribution (OOD) test data. We implement an unsupervised deep neural network-based OOD detector on a real-time embedded autonomous Duckiebot and evaluate detection performance. Our OOD detector produces a success rate of 87.5% for emergency stopping a Duckiebot on a braking test bed we designed. We also provide case analysis on computing resource challenges specific to the Robot Operating System (ROS) middleware on the Duckiebot.