Narrow Results

The software architecture of a developmental robot is a challenging new research subject. This paper presents a theory of developmental mental architecture. Five architecture types, from the simplest Type-1 (observation-driven Markov decision process) to Type-5 (DOSASE MDP), are introduced. The properties and limitations of a simpler one are discussed before the introduction of the next more complex one. Further, we present the architecture design of the Dav robot, a humanoid robot built in the Embodied Intelligence Laboratory at Michigan State University. The framework of the Dav architecture is hand-designed, but the actual controller is developed, i.e. generated autonomously by the developmental program through real-time, online interactions with the real physical environment. We present the Dav architecture and the major components that realize the architecture. The designed architecture for Dav is the next generation version from its extensively tested predecessor, the SAIL developmental robot. Closely related to the issue of performance metrics, the paper also introduces the notion of intelligence completeness (concept completeness, intelligence-metric completeness, and factor completeness) and establishes the concept of the completeness theorem for developmental robotics.

This paper deals with the mechanical design, system integration, and dynamic walking algorithm of KIBO, an emotional biped humanoid robot that has a facial expression mechanism and various human-interactive devices. To emphasize the aesthetic features and marketability of KIBO, the mechanical design was performed after the exterior design stage to conform to all requirements, particularly constraints imposed by the external appearance and human-like link dimensions. For flexible biped walking, a walking pattern generator with variable walking parameters was developed. The walking pattern generator generates both a walking pattern and a corresponding reference zero-moment point (ZMP) pattern simultaneously. For stable biped walking, a walking control strategy using the ZMP and inertial sensor data was developed. In the strategy, we newly proposed a dual ZMP control approach and a posture control approach using an equivalent body inclination, which is calculated from the ZMP and inertial sensor data for robust walking on non-level ground. Finally, the hardware, software architecture, and dynamic walking performance of KIBO were verified through several walking experiments.

Embodiment is a key to solving the reliability and alignment issues in the current AI. This is because it imposes consistent constraints on the entire agent-environment interactions and accompanying information without specifying their actual contents, and the constraints are common to those with similar embodiment. The concept of embodiment should be generalized beyond mechanical properties of the body and information structure of sensory signals, encompassing internal organs and metabolism, mental processes, and inter-agent interactions, to “super-embodiment”. It can address sensibilities, values and morals toward artificial humanity, which will be critically important for the next generation AI. [Y. Kuniyoshi, Open-ended intelligence arises from emergence and development from embodiment, J. Robotics Soc. Jpn. 41(7) (2023) 585–590 (in Japanese); Y. Kuniyoshi, Fusing autonomy and sociality via embodied emergence and development of behaviour and cognition from fetal period, Philos. Trans. R. Soc. B: Biol. Sci. 374 (2019) 20180031].