Environment-Centric Active Inference

TL;DR

This paper introduces environment-centric active inference (EC-AIF), redefining the Markov Blanket to include all observable entities, enabling robots to adapt to unintended environmental changes more effectively.

Contribution

The paper proposes a novel environment-centric framework for active inference that includes all observable entities, unlike traditional agent-centric approaches.

Findings

EC-AIF enables robots to respond to environmental changes effectively.

The robot successfully transported objects despite environmental disturbances.

The approach improves robustness to unintended environmental variations.

Abstract

To handle unintended changes in the environment by agents, we propose an environment-centric active inference EC-AIF in which the Markov Blanket of active inference is defined starting from the environment. In normal active inference, the Markov Blanket is defined starting from the agent. That is, first the agent was defined as the entity that performs the "action" such as a robot or a person, then the environment was defined as other people or objects that are directly affected by the agent's "action," and the boundary between the agent and the environment was defined as the Markov Blanket. This agent-centric definition does not allow the agent to respond to unintended changes in the environment caused by factors outside of the defined environment. In the proposed EC-AIF, there is no entity corresponding to an agent. The environment includes all observable things, including people and things conventionally considered to be the environment, as well as entities that perform "actions" such as robots and people. Accordingly, all states, including robots and people, are included in inference targets, eliminating unintended changes in the environment. The EC-AIF was applied to a robot arm and validated with an object transport task by the robot arm. The results showed that the robot arm successfully transported objects while responding to changes in the target position of the object and to changes in the orientation of another robot arm.