A Multi-perspective Approach To Anomaly Detection For Self-aware Embodied Agents

2018/03/17 by Mohamad Baydoun, Baydoun, Mohamad, Mahdyar Ravanbakhsh +13
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #cs.CV

paper · pdf · doi:10.48550/arxiv.1803.06579

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2018

arxiv created 2018/03/17 · arxiv updated 2018/03/20

Abstract

This paper focuses on multi-sensor anomaly detection for moving cognitive agents using both external and private first-person visual observations. Both observation types are used to characterize agents' motion in a given environment. The proposed method generates locally uniform motion models by dividing a Gaussian process that approximates agents' displacements on the scene and provides a Shared Level (SL) self-awareness based on Environment Centered (EC) models. Such models are then used to train in a semi-unsupervised way a set of Generative Adversarial Networks (GANs) that produce an estimation of external and internal parameters of moving agents. Obtained results exemplify the feasibility of using multi-perspective data for predicting and analyzing trajectory information.

Related

• A Benchmark for Unsupervised Anomaly Detection in Multi-Agent Trajectories
• Multimodal Anomaly Detection with a Mixture-of-Experts
• Hierarchy of GANs for learning embodied self-awareness model
• Coupled IGMM-GANs for deep multimodal anomaly detection in human mobility data
• Learning to Communicate and Correct Pose Errors