How Active Inference Could Help Revolutionise Robotics

Abstract

Recent advances in neuroscience have characterised brain function using mathematical formalisms and first principles that may be usefully applied elsewhere. In this paper, we explain how active inference-a well-known description of sentient behaviour from neuroscience-can be exploited in robotics. In short, active inference leverages the processes thought to underwrite human behaviour to build effective autonomous systems. These systems show state-of-the-art performance in several robotics settings; we highlight these and explain how this framework may be used to advance robotics.

Keywords: Bayesian inference; adaptive robots; filtering; free energy; generative model; model-based control; neurotechnology.

Figure 1

Active inference framework (AIF). AIF could engender important advances in estimation, control, planning and learning in robotics with applications including social, industrial and collaborative robotics, body prosthetics and neurotechnology. (A) AIF explained: Blue circles indicate observations while grey circles indicate random variables that need to be inferred. The black arrows indicate causal relationships implicit in a graphical model (e.g., a Bayesian network). The blue arrows indicate the process by which the agent infers future actions and observations. First, the agent infers the current states from available observation modalities (Bayesian fusion). Then, the agent infers the best available course of action by imagining the counterfactual consequences, in terms of future states and observations. These inferential processes are solved by optimising an (expected) free energy functional of beliefs about states and plausible action sequences. AIF generative models may be hierarchical and encode agent’s representations at increasing levels of abstraction and temporal scales. Perception minimises the discrepancy between predictions and input at all levels. The top layer encodes the estimated (and preferred) states of the world—and the bottom layer encodes sensory input. (B) Practical perspectives: AIF can provide context sensitivity, online adaptivity, accurate state tracking, uncertainty resolution and shared control in a neurologically plausible fashion throughout a wide range of applications.