Physical intelligence as a new paradigm

Metin Sitti

doi:10.1016/j.eml.2021.101340

Abstract

Intelligence of physical agents, such as human-made (e.g., robots, autonomous cars) and biological (e.g., animals, plants) ones, is not only enabled by their computational intelligence (CI) in their brain, but also by their physical intelligence (PI) encoded in their body. Therefore, it is essential to advance the PI of human-made agents as much as possible, in addition to their CI, to operate them in unstructured and complex real-world environments like the biological agents. This article gives a perspective on what PI paradigm is, when PI can be more significant and dominant in physical and biological agents at different length scales and how bioinspired and abstract PI methods can be created in agent bodies. PI paradigm aims to synergize and merge many research fields, such as mechanics, materials science, robotics, mechanical design, fluidics, active matter, biology, self-assembly and collective systems, to enable advanced PI capabilities in human-made agent bodies, comparable to the ones observed in biological organisms. Such capabilities would progress the future robots and other machines beyond what can be realized using the current frameworks.

Highlights

Robots and autonomous cars have been entering more and more to our daily lives, such as homes, on and inside our body, buildings, roads, factories, hospitals, agricultural fields, mines and nuclear plants
In very special harsh environments, such as space, nuclear power plants and everywhere after a nuclear reactor or war disaster, where extreme thermal, mechanical and radiation conditions can hinder the operation of electronic devices, physical intelligence (PI) and mechanical devices would be the only option for physical agents at all length scales
In addition to computational intelligence (CI), it is essential to advance the PI to create autonomous machines to operate in complex real-world environments

Summary

Introduction

Robots and autonomous cars have been entering more and more to our daily lives, such as homes, on and inside our body, buildings, roads, factories, hospitals, agricultural fields, mines and nuclear plants. Our advanced individual and collective NI have taken us to the top of the food chain in nature by enabling unprecedented linguistic, social, cultural, scientific, technological, and artistic progress Overall, using their NI and PI, the biological systems at different length scales have evolved to operate and survive just ‘‘good enough’’ in their complex, diverse and resource-limited natural environments. For autonomous human-made agents, while many AI and machine learning researchers are working intensely to create CI tools and methods as good as or even better than the biological NI, above brief overview can show us that advanced PI capabilities have been indispensable to have in agents operating in unstructured complex environments in different length scales, like in the biological systems. In very special harsh environments, such as space, nuclear power plants and everywhere after a nuclear reactor or war disaster, where extreme thermal, mechanical and radiation conditions can hinder the operation of electronic devices, PI and mechanical devices would be the only option for physical agents at all length scales

Methods to create physical intelligence in physical agents

Encoding memory into the agent body

Physical intelligence in a large number of physical agents

Concluding remarks