Active Inference for Integrated State-Estimation, Control, and Learning
This addresses control and learning challenges in robotics, offering improved robustness and adaptability, though it appears incremental by applying an existing neuroscience framework to robotics.
The paper tackles the problem of integrated state-estimation, control, and learning for robotic manipulators using the active inference framework, resulting in adaptive and robust behavior compared to state-of-the-art methods, as validated on a 7 DoF manipulator.
This work presents an approach for control, state-estimation and learning model (hyper)parameters for robotic manipulators. It is based on the active inference framework, prominent in computational neuroscience as a theory of the brain, where behaviour arises from minimizing variational free-energy. The robotic manipulator shows adaptive and robust behaviour compared to state-of-the-art methods. Additionally, we show the exact relationship to classic methods such as PID control. Finally, we show that by learning a temporal parameter and model variances, our approach can deal with unmodelled dynamics, damps oscillations, and is robust against disturbances and poor initial parameters. The approach is validated on the `Franka Emika Panda' 7 DoF manipulator.