Artificial intelligence, situated approach
Encyclopedia
After several decades of success, traditional artificial intelligence
approaches to modeling decision-making, such as expert systems, finite state machines or decision trees reached their limitations in the 1980s when researchers tried to use them to drive real robots in uncertain environments. In fact, classical AI
technologies face intractable issues, such as combinatorial explosion, when confronted with real-world modeling problems, and several directions have been explored by researchers to address these issues. All these approaches focus on modeling intelligence situated in a given environment: they have come to be known as the situated approach to AI.
. As opposed to classical or traditional artificial intelligence
, nouvelle AI purposely avoided the traditional goal of modeling human-level performance, but rather tries to create systems with intelligence at the level of insects, closer to real-world robots. But eventually, at least at MIT new AI did lead to an attempt for humanoid AI in the Cog Project
.
for developing AI
based on a modular decomposition of intelligence. It was made famous by Rodney Brooks
: his subsumption architecture
was one of the earliest attempts to describe a mechanism for developing BBAI. It is extremely popular in robotics
and to a lesser extent to implement intelligent virtual agents
because it allows the successful creation of real-time dynamic systems that can run in complex environments. For example, it underlies the intelligence of the Sony
, Aibo
and many RoboCup
robot teams.
Realizing that in fact all these approaches were aiming at building not an abstract intelligence, but rather an intelligence situated in a given environment, they have come to be known as the situated approach. In fact, this approach stems out from early insights of Alan Turing
, describing the need to build machines equipped with sense organs to learn directly from the real-world instead of focusing on abstract activities, such as playing chess.
, finite state machines (FSA), or expert systems, are based on the traditional or symbolic AI approach. Its main characteristics are:
However, the limits of traditional AI, which goal is to build systems that mimic human intelligence, are well-known: inevitably, a combinatorial explosion of the number of rules occurs due to the complexity of the environment. In fact, it is impossible to predict all the situations that will be encountered by an autonomous entity.
The goal of situated AI is to model entities that are autonomous in their environment. This is achieved thanks to both the intrinsic robustness of the control architecture, and its adaptation capabilities to unforeseen situations.
and cognitive science
, the term situated refers to an agent
which is embedded in an environment. The term situated is commonly used to refer to robot
s, but some researchers argue that software agents can also be situated if:
Examples might include web-based agents, which can alter data or trigger processes (such as purchases) over the Internet, or virtual-reality bots which inhabit and change virtual worlds, such as Second Life
.
Being situated is generally considered to be part of being embodied, but it is useful to consider each perspective individually. The situated perspective emphasizes that intelligent behavior derives from the environment and the agent's interaction
s with it. The nature of these interactions are defined by an agent's embodiment.
or was at least conceived of as running on its own processing thread
. Generally, though, the modules are just abstraction
s. In this respect, situated AI may be seen as a software engineering
approach to AI, perhaps akin to object oriented design
.
Situated AI is often associated with reactive planning
, but the two are not synonymous. Brooks advocated an extreme version of cognitive minimalism which required initially that the behavior modules were finite state machines and thus contained no conventional memory
or learning
. This is associated with reactive AI because reactive AI requires reacting to the current state of the world, not to an agent
's memory or preconception of that world. However, learning is obviously key to realistic strong AI
, so this constraint has been relaxed, though not entirely abandoned.
Artificial intelligence
Artificial intelligence is the intelligence of machines and the branch of computer science that aims to create it. AI textbooks define the field as "the study and design of intelligent agents" where an intelligent agent is a system that perceives its environment and takes actions that maximize its...
approaches to modeling decision-making, such as expert systems, finite state machines or decision trees reached their limitations in the 1980s when researchers tried to use them to drive real robots in uncertain environments. In fact, classical AI
Ai
AI, A.I., Ai, or ai may refer to:- Computers :* Artificial intelligence, a branch of computer science* Ad impression, in online advertising* .ai, the ISO Internet 2-letter country code for Anguilla...
technologies face intractable issues, such as combinatorial explosion, when confronted with real-world modeling problems, and several directions have been explored by researchers to address these issues. All these approaches focus on modeling intelligence situated in a given environment: they have come to be known as the situated approach to AI.
From traditional AI to nouvelle AI
During the late 1980s, the approach now known as nouvelle AI (nouvelle means new in French) was pioneered at the MIT Artificial Intelligence Laboratory by Rodney BrooksRodney Brooks
Rodney Allen Brooks is the former Panasonic professor of robotics at the Massachusetts Institute of Technology. Since 1986 he has authored a series of highly influential papers which have inaugurated a fundamental shift in artificial intelligence research...
. As opposed to classical or traditional artificial intelligence
Artificial intelligence
Artificial intelligence is the intelligence of machines and the branch of computer science that aims to create it. AI textbooks define the field as "the study and design of intelligent agents" where an intelligent agent is a system that perceives its environment and takes actions that maximize its...
, nouvelle AI purposely avoided the traditional goal of modeling human-level performance, but rather tries to create systems with intelligence at the level of insects, closer to real-world robots. But eventually, at least at MIT new AI did lead to an attempt for humanoid AI in the Cog Project
Cog (project)
Cog was a project at the Humanoid Robotics Group of the Massachusetts Institute of Technology. It was based on the hypothesis that human-level intelligence requires gaining experience from interacting with humans, like human infants do. This in turn requires many interactions with humans over a...
.
From nouvelle AI to behavior-based and situated AI
The conceptual shift introduced by nouvelle AI flourished in the robotics area, given way to behavior-based artificial intelligence (BBAI), a methodologyMethodology
Methodology is generally a guideline for solving a problem, with specificcomponents such as phases, tasks, methods, techniques and tools . It can be defined also as follows:...
for developing AI
Ai
AI, A.I., Ai, or ai may refer to:- Computers :* Artificial intelligence, a branch of computer science* Ad impression, in online advertising* .ai, the ISO Internet 2-letter country code for Anguilla...
based on a modular decomposition of intelligence. It was made famous by Rodney Brooks
Rodney Brooks
Rodney Allen Brooks is the former Panasonic professor of robotics at the Massachusetts Institute of Technology. Since 1986 he has authored a series of highly influential papers which have inaugurated a fundamental shift in artificial intelligence research...
: his subsumption architecture
Subsumption architecture
Subsumption architecture is a reactive robot architecture heavily associated with behavior-based robotics. The term was introduced by Rodney Brooks and colleagues in 1986...
was one of the earliest attempts to describe a mechanism for developing BBAI. It is extremely popular in robotics
Robotics
Robotics is the branch of technology that deals with the design, construction, operation, structural disposition, manufacture and application of robots...
and to a lesser extent to implement intelligent virtual agents
Intelligent agent
In artificial intelligence, an intelligent agent is an autonomous entity which observes through sensors and acts upon an environment using actuators and directs its activity towards achieving goals . Intelligent agents may also learn or use knowledge to achieve their goals...
because it allows the successful creation of real-time dynamic systems that can run in complex environments. For example, it underlies the intelligence of the Sony
Sony
, commonly referred to as Sony, is a Japanese multinational conglomerate corporation headquartered in Minato, Tokyo, Japan and the world's fifth largest media conglomerate measured by revenues....
, Aibo
AIBO
AIBO was one of several types of robotic pets designed and manufactured by Sony...
and many RoboCup
RoboCup
RoboCup is an international robotics competition founded in 1997. The aim is to develop autonomous soccer robots with the intention of promoting research and education in the field of artificial intelligence...
robot teams.
Realizing that in fact all these approaches were aiming at building not an abstract intelligence, but rather an intelligence situated in a given environment, they have come to be known as the situated approach. In fact, this approach stems out from early insights of Alan Turing
Alan Turing
Alan Mathison Turing, OBE, FRS , was an English mathematician, logician, cryptanalyst, and computer scientist. He was highly influential in the development of computer science, providing a formalisation of the concepts of "algorithm" and "computation" with the Turing machine, which played a...
, describing the need to build machines equipped with sense organs to learn directly from the real-world instead of focusing on abstract activities, such as playing chess.
Definitions
Classically, a software entity is defined as a simulated element, able to act on itself and on its environment, and which has an internal representation of itself and of the outside world. An entity can communicate with other entities, and its behavior is the consequence of its perceptions, its representations, and its interactions with the other entities.AI loop
Simulating entities in a virtual environment requires simulating the entire process that goes from a perception of the environment, or more generally from a stimulus, to an action on the environment. This process is called the AI loop and technology used to simulate it can be subdivided in two categories. Sensorimotor or low-level AI deals with either the perception problem (what is perceived?) or the animation problem (how actions are executed?). Decisional or high-level AI deals with the action selection problem (what is the most appropriate action in response to a given perception, i.e. what is the most appropriate behavior?).Traditional or symbolic AI
There are two main approaches in decisional AI. The vast majority of the technologies available on the market, such as planning algorithmsAutomated planning and scheduling
Automated planning and scheduling is a branch of artificial intelligence that concerns the realization of strategies or action sequences, typically for execution by intelligent agents, autonomous robots and unmanned vehicles. Unlike classical control and classification problems, the solutions are...
, finite state machines (FSA), or expert systems, are based on the traditional or symbolic AI approach. Its main characteristics are:
- It is top-down: it subdivides, in a recursive manner, a given problem into a series of sub-problems that are supposedly easier to solve.
- It is knowledge-based: it relies on a symbolic description of the world, such as a set of rules.
However, the limits of traditional AI, which goal is to build systems that mimic human intelligence, are well-known: inevitably, a combinatorial explosion of the number of rules occurs due to the complexity of the environment. In fact, it is impossible to predict all the situations that will be encountered by an autonomous entity.
Situated or behavioral AI
In order to address these issues, another approach to decisional AI, also known as situated or behavioral AI, has been proposed. It does not attempt to model systems that produce deductive reasoning processes, but rather systems that behave realistically in their environment. The main characteristics of this approach are the following:- It is bottom-up: it relies on elementary behaviors, which can be combined to implement more complex behaviors.
- It is behavior-based: it does not rely on a symbolic description of the environment, but rather on a model of the interactions of the entities with their environment.
The goal of situated AI is to model entities that are autonomous in their environment. This is achieved thanks to both the intrinsic robustness of the control architecture, and its adaptation capabilities to unforeseen situations.
Situated agents
In artificial intelligenceArtificial intelligence
Artificial intelligence is the intelligence of machines and the branch of computer science that aims to create it. AI textbooks define the field as "the study and design of intelligent agents" where an intelligent agent is a system that perceives its environment and takes actions that maximize its...
and cognitive science
Cognitive science
Cognitive science is the interdisciplinary scientific study of mind and its processes. It examines what cognition is, what it does and how it works. It includes research on how information is processed , represented, and transformed in behaviour, nervous system or machine...
, the term situated refers to an agent
Intelligent agent
In artificial intelligence, an intelligent agent is an autonomous entity which observes through sensors and acts upon an environment using actuators and directs its activity towards achieving goals . Intelligent agents may also learn or use knowledge to achieve their goals...
which is embedded in an environment. The term situated is commonly used to refer to robot
Robot
A robot is a mechanical or virtual intelligent agent that can perform tasks automatically or with guidance, typically by remote control. In practice a robot is usually an electro-mechanical machine that is guided by computer and electronic programming. Robots can be autonomous, semi-autonomous or...
s, but some researchers argue that software agents can also be situated if:
- they exist in a dynamicDynamical systemA dynamical system is a concept in mathematics where a fixed rule describes the time dependence of a point in a geometrical space. Examples include the mathematical models that describe the swinging of a clock pendulum, the flow of water in a pipe, and the number of fish each springtime in a...
(rapidly changing) environment, which - they can manipulate or change through their actions, and which
- they can senseSenseSenses are physiological capacities of organisms that provide inputs for perception. The senses and their operation, classification, and theory are overlapping topics studied by a variety of fields, most notably neuroscience, cognitive psychology , and philosophy of perception...
or perceivePerceptionPerception is the process of attaining awareness or understanding of the environment by organizing and interpreting sensory information. All perception involves signals in the nervous system, which in turn result from physical stimulation of the sense organs...
.
Examples might include web-based agents, which can alter data or trigger processes (such as purchases) over the Internet, or virtual-reality bots which inhabit and change virtual worlds, such as Second Life
Second Life
Second Life is an online virtual world developed by Linden Lab. It was launched on June 23, 2003. A number of free client programs, or Viewers, enable Second Life users, called Residents, to interact with each other through avatars...
.
Being situated is generally considered to be part of being embodied, but it is useful to consider each perspective individually. The situated perspective emphasizes that intelligent behavior derives from the environment and the agent's interaction
Interaction
Interaction is a kind of action that occurs as two or more objects have an effect upon one another. The idea of a two-way effect is essential in the concept of interaction, as opposed to a one-way causal effect...
s with it. The nature of these interactions are defined by an agent's embodiment.
Modular decomposition
The most important attribute of a system driven by situated AI is that the intelligence is controlled by a set of independent semi-autonomous modules. In the original systems, each module was actually a separate devicePeripheral
A peripheral is a device attached to a host computer, but not part of it, and is more or less dependent on the host. It expands the host's capabilities, but does not form part of the core computer architecture....
or was at least conceived of as running on its own processing thread
Thread (computer science)
In computer science, a thread of execution is the smallest unit of processing that can be scheduled by an operating system. The implementation of threads and processes differs from one operating system to another, but in most cases, a thread is contained inside a process...
. Generally, though, the modules are just abstraction
Abstraction
Abstraction is a process by which higher concepts are derived from the usage and classification of literal concepts, first principles, or other methods....
s. In this respect, situated AI may be seen as a software engineering
Software engineering
Software Engineering is the application of a systematic, disciplined, quantifiable approach to the development, operation, and maintenance of software, and the study of these approaches; that is, the application of engineering to software...
approach to AI, perhaps akin to object oriented design
Object-oriented programming
Object-oriented programming is a programming paradigm using "objects" – data structures consisting of data fields and methods together with their interactions – to design applications and computer programs. Programming techniques may include features such as data abstraction,...
.
Situated AI is often associated with reactive planning
Reactive planning
In artificial intelligence, reactive planning denotes a group of techniques for action selection by autonomous agents. These techniques differ from classical planning in two aspects. First, they operate in a timely fashion and hence can cope with highly dynamic and unpredictable environments....
, but the two are not synonymous. Brooks advocated an extreme version of cognitive minimalism which required initially that the behavior modules were finite state machines and thus contained no conventional memory
Memory
In psychology, memory is an organism's ability to store, retain, and recall information and experiences. Traditional studies of memory began in the fields of philosophy, including techniques of artificially enhancing memory....
or learning
Learning
Learning is acquiring new or modifying existing knowledge, behaviors, skills, values, or preferences and may involve synthesizing different types of information. The ability to learn is possessed by humans, animals and some machines. Progress over time tends to follow learning curves.Human learning...
. This is associated with reactive AI because reactive AI requires reacting to the current state of the world, not to an agent
Intelligent agent
In artificial intelligence, an intelligent agent is an autonomous entity which observes through sensors and acts upon an environment using actuators and directs its activity towards achieving goals . Intelligent agents may also learn or use knowledge to achieve their goals...
's memory or preconception of that world. However, learning is obviously key to realistic strong AI
Strong AI
Strong AI is artificial intelligence that matches or exceeds human intelligence — the intelligence of a machine that can successfully perform any intellectual task that a human being can. It is a primary goal of artificial intelligence research and an important topic for science fiction writers and...
, so this constraint has been relaxed, though not entirely abandoned.
Action selection mechanism
The situated AI community has presented several solutions to modeling decision-making processes, also known as action selection mechanisms. The first attempt to solve this problem goes back to subsumption architectures, which were in fact more an implementation technique than an algorithm. However, this attempt paved the way to several others, in particular the free-flow hierarchies and activation networks. A comparison of the structure and performances of these two mechanisms demonstrated the advantage of using free-flow hierarchies in solving the action selection problem. However, motor schemas and process description languages are two other approaches that have been used with success for autonomous robots.Traditional AI
- Decision TreeDecision treeA decision tree is a decision support tool that uses a tree-like graph or model of decisions and their possible consequences, including chance event outcomes, resource costs, and utility. It is one way to display an algorithm. Decision trees are commonly used in operations research, specifically...
- Finite State MachineFinite state machineA finite-state machine or finite-state automaton , or simply a state machine, is a mathematical model used to design computer programs and digital logic circuits. It is conceived as an abstract machine that can be in one of a finite number of states...
- Expert SystemExpert systemIn artificial intelligence, an expert system is a computer system that emulates the decision-making ability of a human expert. Expert systems are designed to solve complex problems by reasoning about knowledge, like an expert, and not by following the procedure of a developer as is the case in...
- Automated Planning and SchedulingAutomated planning and schedulingAutomated planning and scheduling is a branch of artificial intelligence that concerns the realization of strategies or action sequences, typically for execution by intelligent agents, autonomous robots and unmanned vehicles. Unlike classical control and classification problems, the solutions are...
External links
- Article Artificial Intelligence: The situated approach from the Encyclopædia BritannicaEncyclopædia BritannicaThe Encyclopædia Britannica , published by Encyclopædia Britannica, Inc., is a general knowledge English-language encyclopaedia that is available in print, as a DVD, and on the Internet. It is written and continuously updated by about 100 full-time editors and more than 4,000 expert...
- Article What is AI? - Nouvelle AI from AlanTuring.net
- Nouvelle AI - Definition
- Reactive planning and nouvelle AI