An assembly of mechanical and electrical components that allow a robot to physically act upon itself or the environment.
Robots that can foster and maintain emotional relationships with human beings. Such robots not only perceive and respond to human emotion, but also are possessed of an intrinsic emotional system modeled after human beings. For these robots, emotional state is not merely an outward expression, but rather permeates their control architecture and influences their behavior.
The primitive building blocks for robot control and action. Depending on the control architecture, behaviors can be either simple stimulus-response pairings or more complex rule based units for carrying out a particular competency. Behaviors can be sequenced or run in parallel to produce higher-level capabilities.
The means by which agents cope with a changing world using a spectrum of machine learning techniques including reinforcement learning, neural networks, fuzzy logic and evolutionary computing.
The emotional, physical, and mental interactions between agents. This area includes a host of issues such as communication, interference, competition, cooperation, as well as collective and imitative learning.
The principled organization of embedded software components whereby perception, reasoning, and action conspire to produce functionality. This architecture not only provides structure and services, but guides design by imposing methodological constraints on how behavior can be achieved.
Deliberative control architectures use internal, symbolic representations such as maps, models, and knowledge bases to make decisions and mediate actions. These classical AI (Artificial Intelligence) decision processes are structured at a high enough level so as to be understandable (and especially explainable) for the applications programmer.
A reactive control architecture tightly couples perception and action to produce efficient, real-time responses to the environment with little or no mediation of abstract representation.
Humanoid Robotics research includes a rich diversity of projects wherein perception, processing and action are embodied in a recognizably anthropomorphic form in order to emulate some subset of the physical, cognitive and social dimensions of the human body and experience. This work seeks to create a new kind of tool; fundamentally different from any we have yet seen because it is designed to work with humans as well as for them.
The ability to make appropriate decisions and take appropriate actions in the face of uncertainty. The word 'appropriate' is best characterized in context, and with reference to the task at hand. For example, some tasks require that appropriate action maximize efficiency while others may emphasize learning, survivability, robustness, or an ability to communicate. Ultimately, intelligence is in the eye of the beholder. "We know it when we see it."