Automated planning and scheduling is a branch of artificial intelligence that concerns the realisation 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 complex, unknown and have to be discovered and optimised in multidimensional space. // Hondas intelligent humanoid robot AI redirects here. ... A strategy is a long term plan of action designed to achieve a particular goal, as differentiated from tactics or immediate actions with resources at hand. ... Simple reflex agent Learning agent In computer science, an intelligent agent (IA) is a software agent that exhibits some form of artificial intelligence. ... Autonomous robots are robots which can perform desired tasks in unstructured environments without continuous human guidance. ... UAVs in a hangar An unmanned aerial vehicle (UAV) is a pilotless aircraft, controlled either remotely or flown autonomously, used for a number of missions, including reconnaissance and attack roles. ... It has been suggested that this article or section be merged with Control theory. ... A classifier, in linguistics, is a word or morpheme used in some languages in certain contexts to indicate the word class of a noun. ...

In known environments with available models planning can be done offline. Solutions can be found and evaluated prior to execution. In dynamically unknown environments the strategy often needs to be revised online. Models and policies need to be adapted. Solutions usually resort to iterative trial and error processes commonly seen in artificial intelligence. These include dynamic programming, reinforcement learning and combinatorial optimization. A strategy is a long term plan of action designed to achieve a particular goal, as differentiated from tactics or immediate actions with resources at hand. ... Trial and error is a method for obtaining knowledge, both propositional knowledge and know-how. ... // Hondas intelligent humanoid robot AI redirects here. ... In computer science, dynamic programming is a method for reducing the runtime of algorithms exhibiting the properties of overlapping subproblems and optimal substructure, described below. ... Reinforcement learning refers to a class of problems in machine learning which postulate an agent exploring an environment in which the agent perceives its current state and takes actions. ... Combinatorial optimization is a branch of optimization in applied mathematics and computer science, related to operations research, algorithm theory and computational complexity theory. ...

A typical planner takes three inputs: a description of the initial state of the world, a description of the desired goal, and a set of possible actions, all encoded in a formal language such as STRIPS. The planner produces a sequence of actions that lead from the initial state to a state meeting the goal. An alternative language for describing planning problems is that of hierarchical task networks, in which a set of tasks is given, and each task can be either realized by a primitive action or decomposed in a set of other tasks. The term strips has various meanings: A financial option composed of one call option and two put options with the same strike price A treasury security acronym for Separate Trading of Registered Interest and Principal of Securities, which are the securities obtained when trading the coupons and principal of bonds... In artificial intelligence, the hierarchical task network, or HTN, is an approach to automated planning in which the dependency among actions can be given in the form of networks. ...

The difficulty of planning is dependent on the simplifying assumptions employed, e.g. atomic time, deterministic time, complete observability, etc. Classical planners make all these assumptions and have been studied most fully. Some popular techniques include: forward chaining and backward chaining state-space search, possibly enhanced by the use of relationships among conditions (see graphplan) or heuristics synthesized from the problem, search through plan space, and translation to propositional satisfiability (satplan). Forward chaining is one of the two main methods of reasoning when using inference rules (in artificial intelligence). ... Backward chaining is one of the two main methods of reasoning when using inference rules. ... Graphplan is an algorithm for automated planning developed by Avrim Blum and Merrick Furst in 1995. ... In computer science, besides the common use as rule of thumb (see heuristic), the term heuristic has two well-defined technical meanings. ... Satplan is a method for automated planning. ...

If the assumption of determinism is dropped and a probabalistic model of uncertainty is adopted, then this leads to the problem of policy generation for a Markov decision process (MDP) or (in the general case) Partially observable Markov decision process (POMDP). To meet Wikipedias quality standards, this article or section may require cleanup. ... Overview The Partially Observable Markov Decision Process (POMDP) is an extension of the Markov Decision Process. ...

External Links

• Advanced Planning Systems, Optimisation

See also

• Strategic planning
• Strategy (game theory)
• Markov chain
• Software agent
• Message passing
• Actor model
• Constraint programming
• Multi-agent planning
• Evolutionary computation
• Planning
• Scheduling
• Reactive planning
• Schedulizer