Thursday, September 17, 2015

What is an autonomous system? Are we talking about the same things?

 by Curtis Blais, NPS Faculty Associate Research, clblais(at)nps.edu

 I enjoy reading the monthly articles in the CRUSER Newsletter. We are challenged intellectually by new ideas and even by the different terms used in talking about robotic systems. For example, in the January 2015 issue, Paul Scharre (“The Coming Swarm”) spoke of human-inhabited and uninhabited systems, with the statement that incorporation of increasing automation in uninhabited systems helps them become “true robotic systems.” Such concepts make one wonder how to classify the emerging “driverless” automobiles that transport humans and allow human override, or autonomous medical evacuation aircraft transporting human casualties – are those “true robotic systems”?

Clearly, a challenge in new fields of research and technology is reaching common agreement and use of terminology. In the Department of Defense, the robotics field has emerged rapidly as a revolution in warfighting, potentially reshaping the future battlefield in ways that we are only beginning to discover. In 2008, the National Institute of Standards and Technology issued Special Publication 1011-I-2.0 titled “Autonomy Levels for Unmanned Systems (ALFUS) Framework, Volume 1: Terminology,” in an attempt to standardize terminology for this field. In this report, we find the following definitions that can help focus CRUSER concerns:

Unmanned Systems (UMS): A powered physical system, with no human operator aboard the principal components, which acts in the physical world to accomplish assigned tasks. It may be mobile or stationary. It can include any and all associated supporting components such as OCUs [Operator Control Units, the computer(s), accessories, and data link equipment that an operator uses to control, communicate with, receive data and information from, and plan missions for one or more UMSs]. Examples include unmanned ground vehicles (UGV), unmanned aerial vehicles/systems (UAV/ UAS), unmanned maritime vehicles (UMV) —whether unmanned underwater vehicles (UUV) or unmanned water surface borne vehicles (USV)—unattended munitions (UM), and unattended ground sensors (UGS). Missiles, rockets, and their submunitions, and artillery are not considered the principal components of UMSs.

Autonomy: A UMS’s own ability of integrated sensing, perceiving, analyzing, communicating, planning, decision-making, and acting/executing, to achieve its goals as assigned by its human operator(s) through designed Human-Robot Interface (HRI) or by another system that the UMS communicates with. UMS’s Autonomy is characterized into levels from the perspective of Human Independence (HI), the inverse of HRI. Autonomy is further characterized in terms of Contextual Autonomous Capability (CAC). A UMS’s CAC is characterized by the missions that the system is capable of performing, the environments within which the missions are performed, and human independence that can be allowed in the performance of the missions.

Autonomous: Operations of a UMS wherein the UMS receives its mission from either the operator who is off the UMS or another system that the UMS interacts with and accomplishes that mission with or without further human-robot interaction.

Fully autonomous: A mode of UMS operation wherein the UMS accomplishes it assigned mission, within a defined scope, without human intervention while adapting to operational and environmental conditions.

Semi-autonomous: A mode of UMS operation wherein the human operator and/or the UMS plan(s) and conduct(s) a mission and requires various levels of HRI. The UMS is capable of autonomous operation in between the human interactions.

Remote control: A mode of UMS operation wherein the human operator controls the UMS on a continuous basis, from a location off the UMS via only her/his direct observation. In this mode, the UMS takes no initiative and relies on continuous or nearly continuous input from the human operator.

Teleoperation: A mode of UMS operation wherein the human operator, using sensory feedback, either directly controls the actuators or assigns incremental goals on a continuous basis, from a location off the UMS.

Under CRUSER auspices, the author of the present article is investigating how behaviors and effects of human and unmanned systems can be distinguished in simulation models (see the January 2015 issue of CRUSER News). From the above definitions, we could ask a fundamental question, “Should human warfighters be considered as fully autonomous or semi-autonomous entities?” We probably are quick to consider human warfighters (soldier, sailor, Marine, airman, etc.) as fully autonomous entities, even though they report to some higher command and their actions can be overridden by modified orders from higher command (and, those orders are subject to interpretation, which may or may not correctly align with the commander’s intent, and even so are not guaranteed to be obeyed). Suffice to say, we are in the early stages of a fascinating era of research and development that will bring about greater precision in our concepts and terminology relating to unmanned systems, while possibly redefining our notions of manned systems as well.

Reprinted with permission from thConsortium for Robotics and Unmanned Systems Education and Research (CRUSER).

No comments:

Post a Comment