Deep Active Inference for Autonomous Robot Navigation

Active inference is a theory that underpins the way biological agent's perceive and act in the real world. At its core, active inference is based on the principle that the brain is an approximate Bayesian inference engine, building an internal generative model to drive agents towards minimal surprise. Although this theory has shown interesting results with grounding in cognitive neuroscience, its application remains limited to simulations with small, predefined sensor and state spaces. In this paper, we leverage recent advances in deep learning to build more complex generative models that can work without a predefined states space. State representations are learned end-to-end from real-world, high-dimensional sensory data such as camera frames. We also show that these generative models can be used to engage in active inference. To the best of our knowledge this is the first application of deep active inference for a real-world robot navigation task.

[1]  Raymond J. Dolan,et al.  The anatomy of choice: active inference and agency , 2013, Front. Hum. Neurosci..

[2]  Tim Verbelen,et al.  Bayesian policy selection using active inference , 2019, ICLR 2019.

[3]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

[4]  Kai Ueltzhöffer,et al.  Deep active inference , 2017, Biological Cybernetics.

[5]  Karl J. Friston Life as we know it , 2013, Journal of The Royal Society Interface.

[6]  Raymond J. Dolan,et al.  The anatomy of choice: dopamine and decision-making , 2014, Philosophical Transactions of the Royal Society B: Biological Sciences.

[7]  Karl J. Friston,et al.  A Free Energy Principle for Biological Systems. , 2012, Entropy.

[8]  Beren Millidge,et al.  Deep Active Inference as Variational Policy Gradients , 2019, Journal of Mathematical Psychology.

[9]  Karl J. Friston,et al.  Active Inference: A Process Theory , 2017, Neural Computation.

[10]  Karl J. Friston,et al.  Neuroscience and Biobehavioral Reviews , 2022 .

[11]  Karl J. Friston,et al.  Active Inference in OpenAI Gym: A Paradigm for Computational Investigations Into Psychiatric Illness. , 2018, Biological psychiatry. Cognitive neuroscience and neuroimaging.

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

[13]  Karl J. Friston,et al.  Reinforcement Learning or Active Inference? , 2009, PloS one.

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

[15]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[16]  Tim Verbelen,et al.  Learning Perception and Planning With Deep Active Inference , 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).