Active Inference for Fault Tolerant Control of Robot Manipulators with Sensory Faults

We present a fault tolerant control scheme for robot manipulators based on active inference. The proposed solution makes use of the sensory prediction errors in the free-energy to simplify the residuals and thresholds generation for fault detection and isolation and does not require additional controllers for fault recovery. Results validating the benefits in a simulated 2DOF manipulator are presented and the limitations of the current approach are highlighted.

[1]  Kumpati S. Narendra,et al.  Adaptive control using multiple models , 1997, IEEE Trans. Autom. Control..

[2]  Jie Chen,et al.  Robust Model-Based Fault Diagnosis for Dynamic Systems , 1998, The International Series on Asian Studies in Computer and Information Science.

[3]  Youmin Zhang,et al.  Bibliographical review on reconfigurable fault-tolerant control systems , 2003, Annu. Rev. Control..

[4]  Hassan K. Khalil,et al.  High-gain observers in nonlinear feedback control , 2009, 2009 IEEE International Conference on Control and Automation.

[5]  Karl J. Friston The free-energy principle: a unified brain theory? , 2010, Nature Reviews Neuroscience.

[6]  Karl J. Friston,et al.  Action and behavior: a free-energy formulation , 2010, Biological Cybernetics.

[7]  Massimiliano Mattei,et al.  Robust fault detection and isolation for proprioceptive sensors of robot manipulators , 2010 .

[8]  Karl J. Friston,et al.  Action understanding and active inference , 2011, Biological Cybernetics.

[9]  Karl J. Friston,et al.  Active inference and robot control: a case study , 2016, Journal of The Royal Society Interface.

[10]  Shuzhi Sam Ge,et al.  Fault Diagnosis in Image-Based Visual Servoing With Eye-in-Hand Configurations Using Kalman Filter , 2016, IEEE Transactions on Industrial Informatics.

[11]  Simon McGregor,et al.  The free energy principle for action and perception: A mathematical review , 2017, 1705.09156.

[12]  Rafal Bogacz,et al.  A tutorial on the free-energy framework for modelling perception and learning , 2017, Journal of mathematical psychology.

[13]  Christopher L. Buckley,et al.  A Probabilistic Interpretation of PID Controllers Using Active Inference , 2018, SAB.

[14]  Gordon Cheng,et al.  Adaptive Robot Body Learning and Estimation Through Predictive Coding , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[15]  Gordon Cheng,et al.  Active inference with function learning for robot body perception , 2018 .

[16]  Gordon Cheng,et al.  Active inference body perception and action for humanoid robots , 2019, ArXiv.

[17]  Manuel Baltieri,et al.  PID Control as a Process of Active Inference with Linear Generative Models † , 2019, Entropy.

[18]  Thijs van de Laar,et al.  Simulating Active Inference Processes by Message Passing , 2019, Front. Robot. AI.

[19]  Bert de Vries,et al.  Simulating Active Inference Processes by Message Passing , 2019, Frontiers Robotics AI.

[20]  Active inference for Robot control: A Factor Graph Approach , 2019 .

[21]  Pablo Lanillos,et al.  End-to-End Pixel-Based Deep Active Inference for Body Perception and Action , 2019, 2020 Joint IEEE 10th International Conference on Development and Learning and Epigenetic Robotics (ICDL-EpiRob).

[22]  Riccardo M. G. Ferrari,et al.  A Novel Adaptive Controller for Robot Manipulators Based on Active Inference , 2019, IEEE Robotics and Automation Letters.

[23]  Nick Hawes,et al.  Adaptive Manipulator Control using Active Inference with Precision Learning , 2020 .

[24]  Mohamed Baioumy,et al.  Variational Inference for Predictive and Reactive Controllers , 2020 .

[25]  Henk Wymeersch,et al.  Application of the Free Energy Principle to Estimation and Control , 2019, IEEE Transactions on Signal Processing.

[26]  Nick Hawes,et al.  Active Inference for Integrated State-Estimation, Control, and Learning , 2020, 2021 IEEE International Conference on Robotics and Automation (ICRA).