Incremental Learning of Abnormalities in Autonomous Systems

In autonomous systems, self-awareness capabilities are useful to allow artificial agents to detect abnormal situations based on previous experiences. This paper presents a method that facilitates the incremental learning of new models by an agent. Available learned models can dynamically generate probabilistic predictions as well as evaluate their mismatch from current observations. Observed mismatches are grouped through an unsupervised learning strategy into different classes, each of them corresponding to a dynamic model in a given region of the state space. Such clusters define switching Dynamic Bayesian Networks (DBNs) employed for predicting future instances and detect anomalies. Inferences generated by several DBNs that use different sensorial data are compared quantitatively. For testing the proposed approach, it is considered the multi-sensorial data generated by a robot performing various tasks in a controlled environment and a real autonomous vehicle moving at a University Campus.

[1]  Karl J. Friston.  The free-energy principle: a rough guide to the brain? , 2009, Trends in Cognitive Sciences.

[2]  Bernd Fritzke,et al.  A Growing Neural Gas Network Learns Topologies , 1994, NIPS.

[3]  Rodolfo Lourenzutti,et al.  The Hellinger distance in Multicriteria Decision Making: An illustration to the TOPSIS and TODIM methods , 2014, Expert Syst. Appl..

[4]  Reid G. Simmons,et al.  Structured control for autonomous robots , 1994, IEEE Trans. Robotics Autom..

[5]  Karl J. Friston,et al.  A free energy principle for the brain , 2006, Journal of Physiology-Paris.

[6]  Jorge Herbert de Lira,et al.  Two-Dimensional Signal and Image Processing , 1989 .

[7]  Hany Farid,et al.  Blind inverse gamma correction , 2001, IEEE Trans. Image Process..

[8]  Robi Polikar,et al.  Incremental Learning of Concept Drift in Nonstationary Environments , 2011, IEEE Transactions on Neural Networks.

[9]  Mordechai Ben-Ari,et al.  Robots and Their Applications , 2018 .

[10]  Mahdyar Ravanbakhsh,et al.  a Multi-Perspective Approach to Anomaly Detection for Self -Aware Embodied Agents , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[11]  Emilio Frazzoli,et al.  Real-Time Motion Planning for Agile Autonomous Vehicles , 2000 .

[12]  Carlo S. Regazzoni,et al.  Learning Switching Models for Abnormality Detection for Autonomous Driving , 2018, 2018 21st International Conference on Information Fusion (FUSION).

[13]  Yoshua Bengio,et al.  An Empirical Investigation of Catastrophic Forgeting in Gradient-Based Neural Networks , 2013, ICLR.

[14]  Shuicheng Yan,et al.  Hierarchical Contextual Refinement Networks for Human Pose Estimation , 2019, IEEE Transactions on Image Processing.

[15]  James L. Crowley,et al.  Incremental supervised learning for mobile robot reactive control , 1997, Robotics Auton. Syst..

[16]  Sarwar Hussain Paplu,et al.  Real-Time Recognition of Extroversion-Introversion Trait in Context of Human-Robot Interaction , 2018, Advances in Service and Industrial Robotics.

[17]  Felipe Leno da Silva,et al.  A Survey on Transfer Learning for Multiagent Reinforcement Learning Systems , 2019, J. Artif. Intell. Res..

[18]  E. Feron,et al.  Real-time motion planning for agile autonomous vehicles , 2000, Proceedings of the 2001 American Control Conference. (Cat. No.01CH37148).

[19]  Karl J. Friston,et al.  Bayesian state estimation using generalized coordinates , 2011, Defense + Commercial Sensing.

[20]  Karl J. Friston,et al.  Predictive coding under the free-energy principle , 2009, Philosophical Transactions of the Royal Society B: Biological Sciences.

[21]  Daoyi Dong,et al.  Incremental Reinforcement Learning With Prioritized Sweeping for Dynamic Environments , 2019, IEEE/ASME Transactions on Mechatronics.

[22]  Carlo S. Regazzoni,et al.  Learning Multi-Modal Self-Awareness Models for Autonomous Vehicles from Human Driving , 2018, 2018 21st International Conference on Information Fusion (FUSION).

[23]  Giorgio Metta,et al.  Incremental learning of robot dynamics using random features , 2011, 2011 IEEE International Conference on Robotics and Automation.