Wataru Ohata

Takazumi Matsumoto, Wataru Ohata, Fabien C. Y. Benureau et al.

We show that goal-directed action planning and generation in a teleological framework can be formulated using the free energy principle. The proposed model, which is built on a variational recurrent neural network model, is characterized by three essential features. These are that (1) goals can be specified for both static sensory states, e.g., for goal images to be reached and dynamic processes, e.g., for moving around an object, (2) the model can not only generate goal-directed action plans, but can also understand goals by sensory observation, and (3) the model generates future action plans for given goals based on the best estimate of the current state, inferred using past sensory observations. The proposed model is evaluated by conducting experiments on a simulated mobile agent as well as on a real humanoid robot performing object manipulation.

Pablo Lanillos, Cristian Meo, Corrado Pezzato et al.

Active inference is a mathematical framework which originated in computational neuroscience as a theory of how the brain implements action, perception and learning. Recently, it has been shown to be a promising approach to the problems of state-estimation and control under uncertainty, as well as a foundation for the construction of goal-driven behaviours in robotics and artificial agents in general. Here, we review the state-of-the-art theory and implementations of active inference for state-estimation, control, planning and learning; describing current achievements with a particular focus on robotics. We showcase relevant experiments that illustrate its potential in terms of adaptation, generalization and robustness. Furthermore, we connect this approach with other frameworks and discuss its expected benefits and challenges: a unified framework with functional biological plausibility using variational Bayesian inference.

Hayato Idei, Wataru Ohata, Yuichi Yamashita et al.

The brain attenuates its responses to self-produced exteroceptions (e.g., we cannot tickle ourselves). Is this phenomenon, known as sensory attenuation, enabled innately, or acquired through learning? Here, our simulation study using a multimodal hierarchical recurrent neural network model, based on variational free-energy minimization, shows that a mechanism for sensory attenuation can develop through learning of two distinct types of sensorimotor experience, involving self-produced or externally produced exteroceptions. For each sensorimotor context, a particular free-energy state emerged through interaction between top-down prediction with precision and bottom-up sensory prediction error from each sensory area. The executive area in the network served as an information hub. Consequently, shifts between the two sensorimotor contexts triggered transitions from one free-energy state to another in the network via executive control, which caused shifts between attenuating and amplifying prediction-error-induced responses in the sensory areas. This study situates emergence of sensory attenuation (or self-other distinction) in development of distinct free-energy states in the dynamic hierarchical neural system.

Wataru Ohata, Jun Tani

When agents interact socially with different intentions, conflicts are difficult to avoid. Although how agents can resolve such problems autonomously has not been determined, dynamic characteristics of agency may shed light on underlying mechanisms. The current study focused on the sense of agency (SoA), a specific aspect of agency referring to congruence between the agent's intention in acting and the outcome. Employing predictive coding and active inference as theoretical frameworks of perception and action generation, we hypothesize that regulation of complexity in the evidence lower bound of an agent's model should affect the strength of the agent's SoA and should have a critical impact on social interactions. We built a computational model of imitative interaction between a robot and a human via visuo-proprioceptive sensation with a variational Bayes recurrent neural network, and simulated the model in the form of pseudo-imitative interaction using recorded human body movement data. A key feature of the model is that each modality's complexity can be regulated differently with a hyperparameter assigned to each module. We first searched for an optimal setting that endows the model with appropriate coordination of multimodal sensation. This revealed that the vision module's complexity should be more tightly regulated than that of the proprioception module. Using the optimally trained model, we examined how changing the tightness of complexity regulation after training affects the strength of the SoA during interactions. The results showed that with looser regulation, an agent tends to act more egocentrically, without adapting to the other. In contrast, with tighter regulation, the agent tends to follow the other by adjusting its intention. We conclude that the tightness of complexity regulation crucially affects the strength of the SoA and the dynamics of interactions between agents.