2021 European Control Conference (ECC) · 2021 · 16 citations · 26 references
EngineeringMechanical EngineeringRobotics EngineeringFault-tolerant SystemsRobot ControlRoboticsFault DetectionFault RecoveryFault-tolerant ControlRobot SensorsActive Fault-tolerant ControlActive InferenceFault Detection In Control SystemsFault Detection In Robotic SystemsRobust Fault-tolerant ControlSensory Prediction ErrorState Estimation Under FaultsThresholds
This work presents a novel fault-tolerant control scheme based on active inference. Specifically, a new formulation of active inference which, unlike previous solutions, provides unbiased state estimation and simplifies the definition of probabilistically robust thresholds for fault-tolerant control of robotic systems using the free-energy. The proposed solution makes use of the sensory prediction errors in the free-energy for the generation of residuals and thresholds for fault detection and isolation of sensory faults, and it does not require additional controllers for fault recovery. Results validating the benefits in a simulated 2-DOF manipulator are presented, and future directions to improve the current fault recovery approach are discussed.
26
Robotics: modelling, planning and control
Bruno Siciliano, L. Sciavicco, Luigi Villani et al. · Choice Reviews Online · 2009 · 2.5K citations
Engineering, Mechanical Engineering, Robotics Engineering +17
Variational free energy and the Laplace approximation
Karl Friston, Jérémie Mattout, Nelson J. Trujillo‐Barreto et al. · NeuroImage · 2006 · 952 citations
Action understanding and active inference
Karl Friston, Jérémie Mattout, James M. Kilner · Biological Cybernetics · 2011 · 668 citations