Misplaced Pages

#43956

66-621: Behavior-based robotics sets itself apart from traditional artificial intelligence by using biological systems as a model. Classic artificial intelligence typically uses a set of steps to solve problems, it follows a path based on internal representations of events compared to the behavior-based approach. Rather than use preset calculations to tackle a situation, behavior-based robotics relies on adaptability. This advancement has allowed behavior-based robotics to become commonplace in researching and data gathering. Most behavior-based systems are also reactive , which means they need no programming of what

132-581: A loss function . Variants of gradient descent are commonly used to train neural networks. Another type of local search is evolutionary computation , which aims to iteratively improve a set of candidate solutions by "mutating" and "recombining" them, selecting only the fittest to survive each generation. Distributed search processes can coordinate via swarm intelligence algorithms. Two popular swarm algorithms used in search are particle swarm optimization (inspired by bird flocking ) and ant colony optimization (inspired by ant trails ). Formal logic

198-472: A "degree of truth" between 0 and 1. It can therefore handle propositions that are vague and partially true. Non-monotonic logics , including logic programming with negation as failure , are designed to handle default reasoning . Other specialized versions of logic have been developed to describe many complex domains. Many problems in AI (including in reasoning, planning, learning, perception, and robotics) require

264-515: A chair looks like, or what kind of surface the robot is moving on. Instead, all the information is gleaned from the input of the robot's sensors. The robot uses that information to gradually correct its actions according to the changes in immediate environment. Behavior-based robots (BBR) usually show more biological-appearing actions than their computing -intensive counterparts, which are very deliberate in their actions. A BBR often makes mistakes, repeats actions, and appears confused, but can also show

330-460: A contradiction from premises that include the negation of the problem to be solved. Inference in both Horn clause logic and first-order logic is undecidable , and therefore intractable . However, backward reasoning with Horn clauses, which underpins computation in the logic programming language Prolog , is Turing complete . Moreover, its efficiency is competitive with computation in other symbolic programming languages. Fuzzy logic assigns

396-437: A decrease in the number of academic disciplines. One key question is how well the challenge can be decomposed into subparts, and then addressed via the distributed knowledge in the community. The lack of shared vocabulary between people and communication overhead can sometimes be an issue in these communities and projects. If challenges of a particular type need to be repeatedly addressed so that each one can be properly decomposed,

462-554: A foundation to help the robots learn and succeed. Rather than build world models, behavior-based robots simply react to their environment and problems within that environment. They draw upon internal knowledge learned from their past experiences combined with their basic behaviors to resolve problems. The school of behavior-based robots owes much to work undertaken in the 1980s at the Massachusetts Institute of Technology by Rodney Brooks , who with students and colleagues built

528-415: A multidisciplinary community can be exceptionally efficient and effective. There are many examples of a particular idea appearing in different academic disciplines, all of which came about around the same time. One example of this scenario is the shift from the approach of focusing on sensory awareness of the whole, "an attention to the 'total field ' ", a "sense of the whole pattern, of form and function as

594-429: A path to a target goal, a process called means-ends analysis . Simple exhaustive searches are rarely sufficient for most real-world problems: the search space (the number of places to search) quickly grows to astronomical numbers . The result is a search that is too slow or never completes. " Heuristics " or "rules of thumb" can help prioritize choices that are more likely to reach a goal. Adversarial search

660-516: A scale, around a norm, hierarchize individuals in relation to one another and, if necessary, disqualify and invalidate." (Foucault, 1975/1979, p. 223) Communities of academic disciplines can be found outside academia within corporations, government agencies, and independent organizations, where they take the form of associations of professionals with common interests and specific knowledge. Such communities include corporate think tanks , NASA , and IUPAC . Communities such as these exist to benefit

726-544: A series of thought experiments demonstrating how simply wired sensor/motor connections can result in some complex-appearing behaviors such as fear and love. Later work in BBR is from the BEAM robotics community, which has built upon the work of Mark Tilden . Tilden was inspired by the reduction in the computational power needed for walking mechanisms from Brooks' experiments (which used one microcontroller for each leg), and further reduced

SECTION 10

#1733202208044

792-430: A series of wheeled and legged robots utilizing the subsumption architecture . Brooks' papers, often written with lighthearted titles such as " Planning is just a way of avoiding figuring out what to do next ", the anthropomorphic qualities of his robots, and the relatively low cost of developing such robots, popularized the behavior-based approach. Brooks' work builds—whether by accident or not—on two prior milestones in

858-721: A tool that can be used for reasoning (using the Bayesian inference algorithm), learning (using the expectation–maximization algorithm ), planning (using decision networks ) and perception (using dynamic Bayesian networks ). Probabilistic algorithms can also be used for filtering, prediction, smoothing, and finding explanations for streams of data, thus helping perception systems analyze processes that occur over time (e.g., hidden Markov models or Kalman filters ). The simplest AI applications can be divided into two types: classifiers (e.g., "if shiny then diamond"), on one hand, and controllers (e.g., "if diamond then pick up"), on

924-418: A transdisciplinary team is more holistic and seeks to relate all disciplines into a coherent whole. Cross-disciplinary knowledge is that which explains aspects of one discipline in terms of another. Common examples of cross-disciplinary approaches are studies of the physics of music or the politics of literature . Bibliometrics can be used to map several issues in relation to disciplines, for example,

990-445: A unity", an "integral idea of structure and configuration". This has happened in art (in the form of cubism), physics, poetry, communication and educational theory. According to Marshall McLuhan , this paradigm shift was due to the passage from the era of mechanization, which brought sequentiality, to the era of the instant speed of electricity, which brought simultaneity. Multidisciplinary approaches also encourage people to help shape

1056-669: A wide range of techniques, including search and mathematical optimization , formal logic , artificial neural networks , and methods based on statistics , operations research , and economics . AI also draws upon psychology , linguistics , philosophy , neuroscience , and other fields. Artificial intelligence was founded as an academic discipline in 1956, and the field went through multiple cycles of optimism, followed by periods of disappointment and loss of funding, known as AI winter . Funding and interest vastly increased after 2012 when deep learning outperformed previous AI techniques. This growth accelerated further after 2017 with

1122-487: A wide variety of techniques to accomplish the goals above. AI can solve many problems by intelligently searching through many possible solutions. There are two very different kinds of search used in AI: state space search and local search . State space search searches through a tree of possible states to try to find a goal state. For example, planning algorithms search through trees of goals and subgoals, attempting to find

1188-1139: Is intelligence exhibited by machines , particularly computer systems . It is a field of research in computer science that develops and studies methods and software that enable machines to perceive their environment and use learning and intelligence to take actions that maximize their chances of achieving defined goals. Such machines may be called AIs. Some high-profile applications of AI include advanced web search engines (e.g., Google Search ); recommendation systems (used by YouTube , Amazon , and Netflix ); interacting via human speech (e.g., Google Assistant , Siri , and Alexa ); autonomous vehicles (e.g., Waymo ); generative and creative tools (e.g., ChatGPT , and AI art ); and superhuman play and analysis in strategy games (e.g., chess and Go ). However, many AI applications are not perceived as AI: "A lot of cutting edge AI has filtered into general applications, often without being called AI because once something becomes useful enough and common enough it's not labeled AI anymore ." The various subfields of AI research are centered around particular goals and

1254-641: Is a body of knowledge represented in a form that can be used by a program. An ontology is the set of objects, relations, concepts, and properties used by a particular domain of knowledge. Knowledge bases need to represent things such as objects, properties, categories, and relations between objects; situations, events, states, and time; causes and effects; knowledge about knowledge (what we know about what other people know); default reasoning (things that humans assume are true until they are told differently and will remain true even when other facts are changing); and many other aspects and domains of knowledge. Among

1320-459: Is an input, at least one hidden layer of nodes and an output. Each node applies a function and once the weight crosses its specified threshold, the data is transmitted to the next layer. A network is typically called a deep neural network if it has at least 2 hidden layers. Learning algorithms for neural networks use local search to choose the weights that will get the right output for each input during training. The most common training technique

1386-462: Is an interdisciplinary umbrella that comprises systems that recognize, interpret, process, or simulate human feeling, emotion, and mood . For example, some virtual assistants are programmed to speak conversationally or even to banter humorously; it makes them appear more sensitive to the emotional dynamics of human interaction, or to otherwise facilitate human–computer interaction . However, this tends to give naïve users an unrealistic conception of

SECTION 20

#1733202208044

1452-444: Is an unsolved problem. Knowledge representation and knowledge engineering allow AI programs to answer questions intelligently and make deductions about real-world facts. Formal knowledge representations are used in content-based indexing and retrieval, scene interpretation, clinical decision support, knowledge discovery (mining "interesting" and actionable inferences from large databases ), and other areas. A knowledge base

1518-422: Is anything that perceives and takes actions in the world. A rational agent has goals or preferences and takes actions to make them happen. In automated planning , the agent has a specific goal. In automated decision-making , the agent has preferences—there are some situations it would prefer to be in, and some situations it is trying to avoid. The decision-making agent assigns a number to each situation (called

1584-413: Is classified based on previous experience. There are many kinds of classifiers in use. The decision tree is the simplest and most widely used symbolic machine learning algorithm. K-nearest neighbor algorithm was the most widely used analogical AI until the mid-1990s, and Kernel methods such as the support vector machine (SVM) displaced k-nearest neighbor in the 1990s. The naive Bayes classifier

1650-413: Is labelled by a solution of the problem and whose leaf nodes are labelled by premises or axioms . In the case of Horn clauses , problem-solving search can be performed by reasoning forwards from the premises or backwards from the problem. In the more general case of the clausal form of first-order logic , resolution is a single, axiom-free rule of inference, in which a problem is solved by proving

1716-427: Is made up of people from different academic disciplines and professions. These people are engaged in working together as equal stakeholders in addressing a common challenge. A multidisciplinary person is one with degrees from two or more academic disciplines. This one person can take the place of two or more people in a multidisciplinary community. Over time, multidisciplinary work does not typically lead to an increase or

1782-400: Is reportedly the "most widely used learner" at Google, due in part to its scalability. Neural networks are also used as classifiers. An artificial neural network is based on a collection of nodes also known as artificial neurons , which loosely model the neurons in a biological brain. It is trained to recognise patterns; once trained, it can recognise those patterns in fresh data. There

1848-425: Is the backpropagation algorithm. Neural networks learn to model complex relationships between inputs and outputs and find patterns in data. In theory, a neural network can learn any function. Field of research An academic discipline or academic field is a subdivision of knowledge that is taught and researched at the college or university level. Disciplines are defined (in part) and recognized by

1914-404: Is the process of proving a new statement ( conclusion ) from other statements that are given and assumed to be true (the premises ). Proofs can be structured as proof trees , in which nodes are labelled by sentences, and children nodes are connected to parent nodes by inference rules . Given a problem and a set of premises, problem-solving reduces to searching for a proof tree whose root node

1980-440: Is used for game-playing programs, such as chess or Go. It searches through a tree of possible moves and counter-moves, looking for a winning position. Local search uses mathematical optimization to find a solution to a problem. It begins with some form of guess and refines it incrementally. Gradient descent is a type of local search that optimizes a set of numerical parameters by incrementally adjusting them to minimize

2046-455: Is used for reasoning and knowledge representation . Formal logic comes in two main forms: propositional logic (which operates on statements that are true or false and uses logical connectives such as "and", "or", "not" and "implies") and predicate logic (which also operates on objects, predicates and relations and uses quantifiers such as " Every X is a Y " and "There are some X s that are Y s"). Deductive reasoning in logic

Behavior-based robotics - Misplaced Pages Continue

2112-436: Is used in AI programs that make decisions that involve other agents. Machine learning is the study of programs that can improve their performance on a given task automatically. It has been a part of AI from the beginning. There are several kinds of machine learning. Unsupervised learning analyzes a stream of data and finds patterns and makes predictions without any other guidance. Supervised learning requires labeling

2178-905: Is when the knowledge gained from one problem is applied to a new problem. Deep learning is a type of machine learning that runs inputs through biologically inspired artificial neural networks for all of these types of learning. Computational learning theory can assess learners by computational complexity , by sample complexity (how much data is required), or by other notions of optimization . Natural language processing (NLP) allows programs to read, write and communicate in human languages such as English . Specific problems include speech recognition , speech synthesis , machine translation , information extraction , information retrieval and question answering . Early work, based on Noam Chomsky 's generative grammar and semantic networks , had difficulty with word-sense disambiguation unless restricted to small domains called " micro-worlds " (due to

2244-411: The academic journals in which research is published, and the learned societies and academic departments or faculties within colleges and universities to which their practitioners belong. Academic disciplines are conventionally divided into the humanities (including philosophy , language , art and cultural studies ), the scientific disciplines (such as physics , chemistry , and biology ),

2310-520: The bar exam , SAT test, GRE test, and many other real-world applications. Machine perception is the ability to use input from sensors (such as cameras, microphones, wireless signals, active lidar , sonar, radar, and tactile sensors ) to deduce aspects of the world. Computer vision is the ability to analyze visual input. The field includes speech recognition , image classification , facial recognition , object recognition , object tracking , and robotic perception . Affective computing

2376-416: The transformer architecture , and by the early 2020s hundreds of billions of dollars were being invested in AI (known as the " AI boom "). The widespread use of AI in the 21st century exposed several unintended consequences and harms in the present and raised concerns about its risks and long-term effects in the future, prompting discussions about regulatory policies to ensure the safety and benefits of

2442-436: The " utility ") that measures how much the agent prefers it. For each possible action, it can calculate the " expected utility ": the utility of all possible outcomes of the action, weighted by the probability that the outcome will occur. It can then choose the action with the maximum expected utility. In classical planning , the agent knows exactly what the effect of any action will be. In most real-world problems, however,

2508-421: The agent can seek information to improve its preferences. Information value theory can be used to weigh the value of exploratory or experimental actions. The space of possible future actions and situations is typically intractably large, so the agents must take actions and evaluate situations while being uncertain of what the outcome will be. A Markov decision process has a transition model that describes

2574-510: The agent may not be certain about the situation they are in (it is "unknown" or "unobservable") and it may not know for certain what will happen after each possible action (it is not "deterministic"). It must choose an action by making a probabilistic guess and then reassess the situation to see if the action worked. In some problems, the agent's preferences may be uncertain, especially if there are other agents or humans involved. These can be learned (e.g., with inverse reinforcement learning ), or

2640-529: The agent to operate with incomplete or uncertain information. AI researchers have devised a number of tools to solve these problems using methods from probability theory and economics. Precise mathematical tools have been developed that analyze how an agent can make choices and plan, using decision theory , decision analysis , and information value theory . These tools include models such as Markov decision processes , dynamic decision networks , game theory and mechanism design . Bayesian networks are

2706-494: The anthropomorphic quality of tenacity. Comparisons between BBRs and insects are frequent because of these actions. BBRs are sometimes considered examples of weak artificial intelligence , although some have claimed they are models of all intelligence. Most behavior-based robots are programmed with a basic set of features to start them off. They are given a behavioral repertoire to work with dictating what behaviors to use and when, obstacle avoidance and battery charging can provide

Behavior-based robotics - Misplaced Pages Continue

2772-418: The arts and social sciences. Communities of academic disciplines would contribute at varying levels of importance during different stages of development. These categories explain how the different academic disciplines interact with one another. Multidisciplinary (or pluridisciplinary) knowledge is associated with more than one existing academic discipline or profession. A multidisciplinary community or project

2838-496: The behavior-based approach. In the 1950s, W. Grey Walter , an English scientist with a background in neurological research, built a pair of vacuum tube -based robots that were exhibited at the 1951 Festival of Britain , and which have simple but effective behavior-based control systems. The second milestone is Valentino Braitenberg's 1984 book, " Vehicles – Experiments in Synthetic Psychology " (MIT Press). He describes

2904-552: The benefit of all societies' growth and wellbeing. Regional examples such as Biopeople and industry-academia initiatives in translational medicine such as SHARE.ku.dk in Denmark provide evidence of the successful endeavour of multidisciplinary innovation and facilitation of the paradigm shift. In practice, transdisciplinary can be thought of as the union of all interdisciplinary efforts. While interdisciplinary teams may be creating new knowledge that lies between several existing disciplines,

2970-648: The common sense knowledge problem ). Margaret Masterman believed that it was meaning and not grammar that was the key to understanding languages, and that thesauri and not dictionaries should be the basis of computational language structure. Modern deep learning techniques for NLP include word embedding (representing words, typically as vectors encoding their meaning), transformers (a deep learning architecture using an attention mechanism), and others. In 2019, generative pre-trained transformer (or "GPT") language models began to generate coherent text, and by 2023, these models were able to get human-level scores on

3036-465: The computational requirements to that of logic chips, transistor -based electronics , and analog circuit design. A different direction of development includes extensions of behavior-based robotics to multi-robot teams. The focus in this work is on developing simple generic mechanisms that result in coordinated group behavior, either implicitly or explicitly. Artificial intelligence Artificial intelligence ( AI ), in its broadest sense,

3102-694: The current physical sciences. Prior to the twentieth century, few opportunities existed for science as an occupation outside the educational system. Higher education provided the institutional structure for scientific investigation, as well as economic support for research and teaching. Soon, the volume of scientific information rapidly increased and researchers realized the importance of concentrating on smaller, narrower fields of scientific activity. Because of this narrowing, scientific specializations emerged. As these specializations developed, modern scientific disciplines in universities also improved their sophistication. Eventually, academia's identified disciplines became

3168-433: The early twentieth century, new academic disciplines such as education and psychology were added. In the 1970s and 1980s, there was an explosion of new academic disciplines focusing on specific themes, such as media studies , women's studies , and Africana studies . Many academic disciplines designed as preparation for careers and professions, such as nursing , hospitality management , and corrections , also emerged in

3234-446: The flow of ideas within and among disciplines (Lindholm-Romantschuk, 1998) or the existence of specific national traditions within disciplines. Scholarly impact and influence of one discipline on another may be understood by analyzing the flow of citations. The Bibliometrics approach is described as straightforward because it is based on simple counting. The method is also objective but the quantitative method may not be compatible with

3300-992: The formal sciences like mathematics and computer science ; the social sciences are sometimes considered a fourth category. Individuals associated with academic disciplines are commonly referred to as experts or specialists . Others, who may have studied liberal arts or systems theory rather than concentrating in a specific academic discipline, are classified as generalists . While academic disciplines in and of themselves are more or less focused practices, scholarly approaches such as multidisciplinarity/interdisciplinarity , transdisciplinarity , and cross-disciplinarity integrate aspects from multiple academic disciplines, therefore addressing any problems that may arise from narrow concentration within specialized fields of study. For example, professionals may encounter trouble communicating across academic disciplines because of differences in language, specified concepts, or methodology. Some researchers believe that academic disciplines may, in

3366-563: The foundations for scholars of specific specialized interests and expertise. An influential critique of the concept of academic disciplines came from Michel Foucault in his 1975 book, Discipline and Punish . Foucault asserts that academic disciplines originate from the same social movements and mechanisms of control that established the modern prison and penal system in eighteenth-century France , and that this fact reveals essential aspects they continue to have in common: "The disciplines characterize, classify, specialize; they distribute along

SECTION 50

#1733202208044

3432-549: The future, be replaced by what is known as Mode 2 or "post-academic science", which involves the acquisition of cross-disciplinary knowledge through the collaboration of specialists from various academic disciplines. It is also known as a field of study , field of inquiry , research field and branch of knowledge . The different terms are used in different countries and fields. The University of Paris in 1231 consisted of four faculties : Theology , Medicine , Canon Law and Arts . Educational institutions originally used

3498-583: The innovation of the future. The political dimensions of forming new multidisciplinary partnerships to solve the so-called societal Grand Challenges were presented in the Innovation Union and in the European Framework Programme, the Horizon 2020 operational overlay. Innovation across academic disciplines is considered the pivotal foresight of the creation of new products, systems, and processes for

3564-440: The intelligence of existing computer agents. Moderate successes related to affective computing include textual sentiment analysis and, more recently, multimodal sentiment analysis , wherein AI classifies the affects displayed by a videotaped subject. A machine with artificial general intelligence should be able to solve a wide variety of problems with breadth and versatility similar to human intelligence . AI research uses

3630-537: The late 1980s and 1990s, methods were developed for dealing with uncertain or incomplete information, employing concepts from probability and economics . Many of these algorithms are insufficient for solving large reasoning problems because they experience a "combinatorial explosion": They become exponentially slower as the problems grow. Even humans rarely use the step-by-step deduction that early AI research could model. They solve most of their problems using fast, intuitive judgments. Accurate and efficient reasoning

3696-457: The most difficult problems in knowledge representation are the breadth of commonsense knowledge (the set of atomic facts that the average person knows is enormous); and the sub-symbolic form of most commonsense knowledge (much of what people know is not represented as "facts" or "statements" that they could express verbally). There is also the difficulty of knowledge acquisition , the problem of obtaining knowledge for AI applications. An "agent"

3762-458: The organizations affiliated with them by providing specialized new ideas, research, and findings. Nations at various developmental stages will find the need for different academic disciplines during different times of growth. A newly developing nation will likely prioritize government, political matters and engineering over those of the humanities, arts and social sciences. On the other hand, a well-developed nation may be capable of investing more in

3828-405: The other hand. Classifiers are functions that use pattern matching to determine the closest match. They can be fine-tuned based on chosen examples using supervised learning . Each pattern (also called an " observation ") is labeled with a certain predefined class. All the observations combined with their class labels are known as a data set . When a new observation is received, that observation

3894-524: The political science field (emphasizing the policy analysis aspect). As the twentieth century approached, these designations were gradually adopted by other countries and became the accepted conventional subjects. However, these designations differed between various countries. In the twentieth century, the natural science disciplines included: physics , chemistry , biology , geology , and astronomy . The social science disciplines included: economics , politics , sociology , and psychology . Prior to

3960-411: The probability that a particular action will change the state in a particular way and a reward function that supplies the utility of each state and the cost of each action. A policy associates a decision with each possible state. The policy could be calculated (e.g., by iteration ), be heuristic , or it can be learned. Game theory describes the rational behavior of multiple interacting agents and

4026-471: The technology . The general problem of simulating (or creating) intelligence has been broken into subproblems. These consist of particular traits or capabilities that researchers expect an intelligent system to display. The traits described below have received the most attention and cover the scope of AI research. Early researchers developed algorithms that imitated step-by-step reasoning that humans use when they solve puzzles or make logical deductions . By

SECTION 60

#1733202208044

4092-717: The term "discipline" to catalog and archive the new and expanding body of information produced by the scholarly community. Disciplinary designations originated in German universities during the beginning of the nineteenth century. Most academic disciplines have their roots in the mid-to-late-nineteenth century secularization of universities, when the traditional curricula were supplemented with non-classical languages and literatures , social sciences such as political science , economics , sociology and public administration , and natural science and technology disciplines such as physics , chemistry , biology , and engineering . In

4158-451: The training data with the expected answers, and comes in two main varieties: classification (where the program must learn to predict what category the input belongs in) and regression (where the program must deduce a numeric function based on numeric input). In reinforcement learning , the agent is rewarded for good responses and punished for bad ones. The agent learns to choose responses that are classified as "good". Transfer learning

4224-424: The twentieth century, categories were broad and general, which was expected due to the lack of interest in science at the time. With rare exceptions, practitioners of science tended to be amateurs and were referred to as "natural historians" and "natural philosophers"—labels that date back to Aristotle—instead of "scientists". Natural history referred to what we now call life sciences and natural philosophy referred to

4290-446: The universities. Finally, interdisciplinary scientific fields of study such as biochemistry and geophysics gained prominence as their contribution to knowledge became widely recognized. Some new disciplines, such as public administration , can be found in more than one disciplinary setting; some public administration programs are associated with business schools (thus emphasizing the public management aspect), while others are linked to

4356-420: The use of particular tools. The traditional goals of AI research include reasoning , knowledge representation , planning , learning , natural language processing , perception, and support for robotics . General intelligence —the ability to complete any task performable by a human on an at least equal level—is among the field's long-term goals. To reach these goals, AI researchers have adapted and integrated

#43956