Human-in-the-loop

Last updated

Human-in-the-loop (HITL) is used in multiple contexts. It can be defined as a model requiring human interaction. [1] [2] HITL is associated with modeling and simulation (M&S) in the live, virtual, and constructive taxonomy. HITL along with the related human-on-the-loop are also used in relation to lethal autonomous weapons. [3] Further, HITL is used in the context of machine learning. [4]

Contents

Machine learning

In machine learning, HITL is used in the sense of humans aiding the computer in making the correct decisions in building a model. [4] HITL improves machine learning over random sampling by selecting the most critical data needed to refine the model. [5]

Simulation

In simulation, HITL models may conform to human factors requirements as in the case of a mockup. In this type of simulation a human is always part of the simulation and consequently influences the outcome in such a way that is difficult if not impossible to reproduce exactly. HITL also readily allows for the identification of problems and requirements that may not be easily identified by other means of simulation.

HITL is often referred to as interactive simulation, which is a special kind of physical simulation in which physical simulations include human operators, such as in a flight or a driving simulator.

Benefits

Human-in-the-loop allows the user to change the outcome of an event or process. The immersion effectively contributes to a positive transfer of acquired skills into the real world. This can be demonstrated by trainees utilizing flight simulators in preparation to become pilots.

HITL also allows for the acquisition of knowledge regarding how a new process may affect a particular event. Utilizing HITL allows participants to interact with realistic models and attempt to perform as they would in an actual scenario. HITL simulations bring to the surface issues that would not otherwise be apparent until after a new process has been deployed. A real-world example of HITL simulation as an evaluation tool is its usage by the Federal Aviation Administration (FAA) to allow air traffic controllers to test new automation procedures by directing the activities of simulated air traffic while monitoring the effect of the newly implemented procedures. [6]

As with most processes, there is always the possibility of human error, which can only be reproduced using HITL simulation. Although much can be done to automate systems, humans typically still need to take the information provided by a system to determine the next course of action based on their judgment and experience. Intelligent systems can only go so far in certain circumstances to automate a process; only humans in the simulation can accurately judge the final design. Tabletop simulation may be useful in the very early stages of project development for the purpose of collecting data to set broad parameters, but the important decisions require human-in-the-loop simulation. [7]

Within virtual simulation taxonomy

Virtual simulations inject HITL in a central role by exercising motor control skills (e.g. flying an airplane), decision making skills (e.g. committing fire control resources to action), or communication skills (e.g. as members of a C4I team).

Examples

Misconceptions

Although human-in-the-loop simulation can include a computer simulation in the form of a synthetic environment, computer simulation is not necessarily a form of human-in-the-loop simulation, and is often considered as human-out-of-the loop simulation. In this particular case, a computer model’s behavior is modified according to a set of initial parameters. The results of the model differ from the results stemming from a true human-in-the-loop simulation because the results can easily be replicated time and time again, by simply providing identical parameters.

Weapons

Three classifications of the degree of human control of autonomous weapon systems were laid out by Bonnie Docherty in a 2012 Human Rights Watch report. [3]

See also

Related Research Articles

<span class="mw-page-title-main">Simulation</span> Imitation of the operation of a real-world process or system over time

A simulation is an imitative representation of a process or system that could exist in the real world. In this broad sense, simulation can often be used interchangeably with model. Sometimes a clear distinction between the two terms is made, in which simulations require the use of models; the model represents the key characteristics or behaviors of the selected system or process, whereas the simulation represents the evolution of the model over time. Another way to distinguish between the terms is to define simulation as experimentation with the help of a model. This definition includes time-independent simulations. Often, computers are used to execute the simulation.

Reinforcement learning (RL) is an interdisciplinary area of machine learning and optimal control concerned with how an intelligent agent ought to take actions in a dynamic environment in order to maximize the cumulative reward. Reinforcement learning is one of three basic machine learning paradigms, alongside supervised learning and unsupervised learning.

<span class="mw-page-title-main">Flight simulator</span> Technology used for training aircrew

A flight simulator is a device that artificially re-creates aircraft flight and the environment in which it flies, for pilot training, design, or other purposes. It includes replicating the equations that govern how aircraft fly, how they react to applications of flight controls, the effects of other aircraft systems, and how the aircraft reacts to external factors such as air density, turbulence, wind shear, cloud, precipitation, etc. Flight simulation is used for a variety of reasons, including flight training, the design and development of the aircraft itself, and research into aircraft characteristics and control handling qualities.

<span class="mw-page-title-main">Training</span> Acquisition of knowledge, skills, and competencies as a result of teaching or practice

Training is teaching, or developing in oneself or others, any skills and knowledge or fitness that relate to specific useful competencies. Training has specific goals of improving one's capability, capacity, productivity and performance. It forms the core of apprenticeships and provides the backbone of content at institutes of technology. In addition to the basic training required for a trade, occupation or profession, training may continue beyond initial competence to maintain, upgrade and update skills throughout working life. People within some professions and occupations may refer to this sort of training as professional development. Training also refers to the development of physical fitness related to a specific competence, such as sport, martial arts, military applications and some other occupations.

<span class="mw-page-title-main">Computer simulation</span> Process of mathematical modelling, performed on a computer

Computer simulation is the process of mathematical modelling, performed on a computer, which is designed to predict the behaviour of, or the outcome of, a real-world or physical system. The reliability of some mathematical models can be determined by comparing their results to the real-world outcomes they aim to predict. Computer simulations have become a useful tool for the mathematical modeling of many natural systems in physics, astrophysics, climatology, chemistry, biology and manufacturing, as well as human systems in economics, psychology, social science, health care and engineering. Simulation of a system is represented as the running of the system's model. It can be used to explore and gain new insights into new technology and to estimate the performance of systems too complex for analytical solutions.

X-Plane is a flight simulation software initially launched by Laminar Research in 1995. Commercial desktop versions are sold for macOS, Windows, and Linux. In addition, Laminar Research also distributes FAA-certified versions for professional use. A mobile version has been available for Android, iOS, and webOS since 2009 as well.

<span class="mw-page-title-main">Crowd simulation</span> Model of movement

Crowd simulation is the process of simulating the movement of a large number of entities or characters. It is commonly used to create virtual scenes for visual media like films and video games, and is also used in crisis training, architecture and urban planning, and evacuation simulation.

<span class="mw-page-title-main">Driving simulator</span> Professional simulator designed for beginner drivers

Driving simulators are used for entertainment as well as in training of driver's education courses taught in educational institutions and private businesses. They are also used for research purposes in the area of human factors and medical research, to monitor driver behavior, performance, and attention and in the car industry to design and evaluate new vehicles or new advanced driver assistance systems.

Combat flight simulators are vehicle simulation games, amateur flight simulation computer programs used to simulate military aircraft and their operations. These are distinct from dedicated flight simulators used for professional pilot and military flight training which consist of realistic physical recreations of the actual aircraft cockpit, often with a full-motion platform.

<span class="mw-page-title-main">Motion simulator</span> Type of mechanism

A motion simulator or motion platform is a mechanism that creates the feelings of being in a real motion environment. In a simulator, the movement is synchronised with a visual display of the outside world (OTW) scene. Motion platforms can provide movement in all of the six degrees of freedom (DOF) that can be experienced by an object that is free to move, such as an aircraft or spacecraft:. These are the three rotational degrees of freedom and three translational or linear degrees of freedom.

<span class="mw-page-title-main">User interface design</span> Planned operator–machine interaction

User interface (UI) design or user interface engineering is the design of user interfaces for machines and software, such as computers, home appliances, mobile devices, and other electronic devices, with the focus on maximizing usability and the user experience. In computer or software design, user interface (UI) design primarily focuses on information architecture. It is the process of building interfaces that clearly communicate to the user what's important. UI design refers to graphical user interfaces and other forms of interface design. The goal of user interface design is to make the user's interaction as simple and efficient as possible, in terms of accomplishing user goals.

An intelligent tutoring system (ITS) is a computer system that imitates human tutors and aims to provide immediate and customized instruction or feedback to learners, usually without requiring intervention from a human teacher. ITSs have the common goal of enabling learning in a meaningful and effective manner by using a variety of computing technologies. There are many examples of ITSs being used in both formal education and professional settings in which they have demonstrated their capabilities and limitations. There is a close relationship between intelligent tutoring, cognitive learning theories and design; and there is ongoing research to improve the effectiveness of ITS. An ITS typically aims to replicate the demonstrated benefits of one-to-one, personalized tutoring, in contexts where students would otherwise have access to one-to-many instruction from a single teacher, or no teacher at all. ITSs are often designed with the goal of providing access to high quality education to each and every student.

Business simulation or corporate simulation is simulation used for business training, education or analysis. It can be scenario-based or numeric-based.

Neuroergonomics is the application of neuroscience to ergonomics. Traditional ergonomic studies rely predominantly on psychological explanations to address human factors issues such as: work performance, operational safety, and workplace-related risks. Neuroergonomics, in contrast, addresses the biological substrates of ergonomic concerns, with an emphasis on the role of the human nervous system.

Hardware-in-the-loop (HIL) simulation, or HWIL, is a technique that is used in the development and testing of complex real-time embedded systems. HIL simulation provides an effective testing platform by adding the complexity of the process-actuator system, known as a plant, to the test platform. The complexity of the plant under control is included in testing and development by adding a mathematical representation of all related dynamic systems. These mathematical representations are referred to as the "plant simulation". The embedded system to be tested interacts with this plant simulation.

An instructional simulation, also called an educational simulation, is a simulation of some type of reality but which also includes instructional elements that help a learner explore, navigate or obtain more information about that system or environment that cannot generally be acquired from mere experimentation. Instructional simulations are typically goal oriented and focus learners on specific facts, concepts, or applications of the system or environment. Today, most universities make lifelong learning possible by offering a virtual learning environment (VLE). Not only can users access learning at different times in their lives, but they can also immerse themselves in learning without physically moving to a learning facility, or interact face to face with an instructor in real time. Such VLEs vary widely in interactivity and scope. For example, there are virtual classes, virtual labs, virtual programs, virtual library, virtual training, etc. Researchers have classified VLE in 4 types:

Dynamic decision-making (DDM) is interdependent decision-making that takes place in an environment that changes over time either due to the previous actions of the decision maker or due to events that are outside of the control of the decision maker. In this sense, dynamic decisions, unlike simple and conventional one-time decisions, are typically more complex and occur in real-time and involve observing the extent to which people are able to use their experience to control a particular complex system, including the types of experience that lead to better decisions over time.

The following outline is provided as an overview of and topical guide to robotics:

<span class="mw-page-title-main">Computer-generated imagery</span> Application of computer graphics to create or contribute to images

Computer-generated imagery (CGI) is a specific-technology or application of computer graphics for creating or improving images in art, printed media, simulators, videos and video games. These images are either static or dynamic. CGI both refers to 2D computer graphics and 3D computer graphics with the purpose of designing characters, virtual worlds, or scenes and special effects. The application of CGI for creating/improving animations is called computer animation, or CGI animation.

<span class="mw-page-title-main">Multifidelity simulation</span>

Multifidelity methods leverage both low- and high-fidelity data in order to maximize the accuracy of model estimates, while minimizing the cost associated with parametrization. They have been successfully used in impedance cardiography, wing-design optimization, robotic learning, computational biomechanics, and have more recently been extended to human-in-the-loop systems, such as aerospace and transportation. They include both model-based methods, where a generative model is available or can be learned, in addition to model-free methods, that include regression-based approaches, such as stacked-regression. A more general class of regression-based multi-fidelity methods are Bayesian approaches, e.g. Bayesian linear regression, Gaussian mixture models, Gaussian processes, auto-regressive Gaussian processes, or Bayesian polynomial chaos expansions.

References

  1. "DoD Modeling and Simulation (M&S) Glossary", DoD 5000.59-M, DoD, January 1998 "Directives Division" (PDF). Archived from the original (PDF) on 2007-07-10. Retrieved 2009-04-22.
  2. Karwowski, Waldemar, International encyclopedia of ergonomics and human factors , ISBN   0-415-30430-X, 9780415304306, CRC Press, 2006
  3. 1 2 Amitai Etzioni; Oren Etzioni (June 2017). "Pros and Cons of Autonomous Weapons Systems". army.mil.
  4. 1 2 Vikram Singh Bisen (May 20, 2020). "What is Human in the Loop Machine Learning: Why & How Used in AI?". medium.com.
  5. Chelsea Chandler; Peter W Foltz; Brita Elvevåg (26 May 2022). "Improving the Applicability of AI for Psychiatric Applications through Human-in-the-loop Methodologies". Schizophrenia Bulletin. 48 (5): 949–956. doi:10.1093/schbul/sbac038. PMC   9434423 . PMID   35639561.
  6. Sollenberger, R. (2005). Human-in-the-Loop Simulation Evaluating the Collocation of the User Request Evaluation Tool. U.S. Department of Transportation Federal Aviation Administration, 1. Retrieved July 19, 2010, from http://hf.tc.faa.gov/technotes/dot-faa-ct-tn04-28.pdf Archived 2010-06-09 at the Wayback Machine
  7. Human-in-the-loop simulation: (2007, Spring). Port Technology International, 32, 1-2. Retrieved July 19, 2010, from http://www.marinesafety.com/research/documents/HumanintheloopSimulationasPublishedinPortTechnologyInternationalIssue32.pdf Archived 2011-07-14 at the Wayback Machine
  8. Pinto R, Mettler T, Taisch M (2013), Managing supplier delivery reliability risk under limited information: Foundations for a human-in-the-loop DSS , Decision Support Systems, 54:2, 1076–1084
  9. [Minsky, Kurzweil, Mann, IEEE ISTAS 2013].