Fast, Robust, and Versatile Event Detection through HMM Belief State Gradient Measures. [arxiv]
Shuangqi Luo, Hongmin Wu, Hongbin Lin, Shuangda Duan, Yisheng Guan, and Juan Rojas.

Abstract:
Event detection is a critical feature in data-driven systems as it assists with the identification of nominal and anomalous behavior. Event detection is increasingly relevant in robotics as robots operate with greater autonomy in increasingly unstructured environments. In this work, we present an accurate, robust, fast, and versatile measure for skill and anomaly identification. A theoretical proof establishes the link between the derivative of the log-likelihood of the HMM filtered belief state and the latest emission probabilities. The key insight is the inverse relationship in which gradient analysis is used for skill and anomaly identification. Our measure showed better performance across all metrics than related state-of-the art works. The result is broadly applicable to domains that use HMMs for event detection.

Resources:

• Code
  • All ROS code for smach, motion, and introspection can be found under our birl_baxter_simulator package in the shuangqi_branch:
    https://github.com/birlrobotics/birl_baxter_tasks
• Supplement
  • Supplemental information for theoretical proof in paper here.
• Data
  • Illustrations and a variety of data results comparing metrics and other works are available in this zip (8MB).
  • Additionally, HMM parameter values derived from EM for all models, as well as a variety of Viterbi path visualizations (including plots and graphs) in this zip (8MB).

• Video
  The video shows robustness and versatility experiments both in pre-and post-recovery scenarios.
  YouTube | Youku.

Copyright Notice:
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author’s copyright. These works may not be reposted without the explicit permission of the copyright holder.