TALplanner is a forward-chaining planner that utilizes domain-dependent knowledge to control search in the state space generated by action invocation. The domain-dependent control knowledge, background knowledge, plans, and goals are all represented using formulas in a temporal logic called tal, which has been developed independently as a formalism for specifying agent narratives and reasoning about them. In the Fifth International Artificial Intelligence Planning and Scheduling Conference planning competition, TALplanner exhibited impressive performance, winning the Outstanding Performance Award in the Domain-Dependent Planning Competition. In this article, we provide an overview of TALplanner

The main idea that arise during the forward search phase and of the planner is to compute offline, in the preprocessing the goals. This approach succeeds in the notion of related facts in the goal-regression avoiding computing estimates for invalid facts process. These are facts that have been achieved in the preprocessing phase. However, it introduces either by the same or subsequent actions, without some problems in situations where the the last actions deleting the facts achieved goal state is not completely described because first. The cost of achieving simultaneously a set an action to regress the goals might not exist. of unrelated facts is considered equal to the To cope with this situation, at the beginning sum of their individual costs, whereas the cost of the preprocessing phase, We know from our experience that if move actions were Table 1.

The long-term future of space exploration at the National Aeronautics and Space Administration (NASA) is dependent on the full exploitation of autonomous and adaptive systems, but mission managers are worried about the reliability of these more intelligent systems. The main focus of the workshop was to address these worries; hence, we invited NASA engineers working on autonomous and adaptive systems and researchers interested in the verification and validation of software systems. The dual purpose of the meeting was to (1) make NASA engineers aware of the verification and validation techniques they could be using and (2) make the verification and validation community aware of the complexity of the systems NASA is developing. The workshop was held 5 to 7 December 2000 at the Asilomar Conference Center in Pacific Grove, California.

BDDplan was created to perform certain reasoning processes in the fluent calculus, a flexible framework for reasoning about action and change based on first-order logic with equality (plus some second-order extensions in some cases). The reasoning is done by mapping the problems into propositional logic, which, in turn, can be implemented as operations on binary decision diagrams (BDDs).

A final chapter overviews the avoid being puzzled by the many confusions, to be a "general textbook of problems and the techniques for

Fast-forward (FF) was the most successful automatic planner in the Fifth International Conference on Artificial Intelligence Planning and Scheduling (AIPS '00) planning systems competition. Like the well-known hsp system, FF relies on forward search in the state space, guided by a heuristic that estimates goal distances by ignoring delete lists. It differs from HSP in a number of important details. This article describes the algorithmic techniques used in FF in comparison to hsp and evaluates their benefits in terms of run-time and solution-length behavior.

Other achieves a tradeoff between optimality and heuristic search planners in the AIPS2000 Contest speed. The transition function f maps states s file domain.pddl. The syntax for the instance into states s′ s - Del(a) Add(a) for and domain files is given by the PDDL standard. The action costs c(a) are all equal to 1. that includes The states s S are sets of atoms from can also choose a schedule of options as done A. in The set of actions A(s) applicable in s is found. In addition, the different options can are the operators op in O that are relevant be run concurrently as threads.

All subsequent work considers the obtained Petri net representation. These tokens hold on ction planning is generally done in two (2) searching it for a solution. The way a label of the specific bindings of the variables work load is shared between these stages of the predicate associated with the place. The particularity of our planner lays in the flexibility it offers in the this listing. Indeed, all markings reachable way it builds the search space, which, in turn, in one step are unified in one sole marking: leads to valuable consequences over the search They are superposed, and copies of itself.

Planning domains often feature subproblems such as route planning and resource handling. Using static domain analysis techniques, we have been able to identify certain commonly occurring subproblems within planning domains, making it possible to abstract these subproblems from the overall goals of the planner and deploy specialized technology to handle them in a way integrated with the broader planning activities. Using two such subsolvers our hybrid planner, stan4, participated successfully in the Fifth International Conference on Artificial Intelligence Planning and Scheduling (AIPS'00) planning competition.

The Association for the Advancement of Artificial Intelligence presented the 2000 Fall Symposium Series was held on Friday through Sunday, 3 to 5 November, at the Sea Crest Oceanfront Conference Center. The titles of the five symposia were (1) Building Dialogue Systems for Tutorial Applications, (2) Learning How to Do Things, (3) Parallel Cognition for Embodied Agents, (4) Simulating Human Agents, and (5) Socially Intelligent Agents: The Human in the Loop.