The most common representation formalisms for planning are descriptive models. They abstractly describe what the actions do and are tailored for efficiently computing the next state(s) in a state transition system. But acting requires operational models that describe how to do things, with rich control structures for closed-loop online decision-making. Using descriptive representations for planning and operational representations for acting can lead to problems with developing and verifying consistency of the different models.We define and implement an integrated acting-and-planning system in which both planning and acting use the same operational models, which are written in a general-purpose hierarchical task-oriented language offering rich control structures. The acting component is inspired by the well-known PRS system, except that instead of being purely reactive, it can get advice from the planner. Our planning algorithm, RAEplan, plans by doing Monte Carlo rollout simulations of the actor’s operational models. Our experiments show significant benefits in the efficiency of the acting and planning system.

In a recent position paper in Artificial Intelligence, we argued that the automated planning research literature has underestimated the importance and difficulty of deliberative acting, which is more than just interleaving planning and execution. We called for more research on the AI problems that emerge when attempting to integrate acting with planning. To provide a basis for such research, it will be important to have a formalization of acting that can be useful in practice. This is needed in the same way that a formal account of planning was necessary for research on planning. We describe some first steps toward developing such a formalization, and invite readers to carry out research along this line.

This paper reports on FAPE (Flexible Acting and Planning Environment), a framework integrating acting and planning on the basis of the ANML modeling language. ANML is a recent proposal motivated by combining the expressiveness of the timeline representation with decomposition methods of Hierarchical Task Networks (HTN). Our current focus is not efficient temporal planning per se, but the tight integration of acting and planning. This integration is addressed by: (i) extending HTN methods with the refinement of planned actions with skills, expressed in PRS, to map actions into low-level commands, (ii) interleaving the planning process with acting, the former performs plan repair and replanning, while the latter implements the skill-based refinements, and (iii) executing commands with a dispatching mechanism that synchronizes observed time points of action effects and events with planned time. FAPE has been integrated to a PR2 robot and experimented in a home-like environment. The paper presents how planning is performed and integrated with acting and describes briefly the robotics experiments.

The Rosetta project has to design, and launch a robotic comet lander in 2003 in order to carry out extensive scientific analyse's of the P/Wirtanen comet following a rendezvous in 2011. A mission simulator was developed in order to obtain information on the critical resources of the lander. However, one needs to feed a simulator with realistic task sequences, that is, plans meeting all the constraints and goals of the mission. Such entries are very difficult to obtain through hand coding or even impossible without computations. We propose a general temporal planner, called I/sub X/T/sub E/T, to provide these mission plans as part of the design process. After a brief introduction on the Rosetta project, we present our approach and discuss the advantages and difficulties encountered in using a general temporal planner for the dimensioning and optimisation of the space-robot resources. Results achieved so far are illustrated.

In the MARTHA project, a large number of robots in a harbour are given the global task of transporting containers from one area to another. The global decision-making process of allocating robots to those predefined tasks can be viewed as a scheduling and resource allocation problem, which is addressed here in a centralised way. Imprecision of temporal constraints makes it meaningless to search for a strict optimal schedule. The authors' approach interleaves task allocation and execution, scheduling in a sliding short-term horizon, as the execution process runs, and providing near-optimal solutions. For large applications the complexity of temporal management is a crucial issue. The authors present a graph decomposition technique, leading to nearly-constant time temporal propagation, without any loss of information.

The authors present a method for selecting viewpoints and sensing tasks to confirm by a multisensory perception machine, an identification hypothesis previously generated. The determination relies on the use of a compiled knowledge base that links object and sensor models, and defines a priori the best sensing tasks to be performed. The method is fully detailed, and its use under dynamic constraints due to a real environment is explained, along with a control strategy to activate the search. Result of experiments integrating other modules for environment modeling, path planning and execution control, and object recognition are presented.>

In the context of mobile robot appli- cations for safety surveillance and intervention, we present an execution control approach based on the use of automated deduction. The task, split into prirn- itiue actions, is described by a graph in a proposi- tional logic which links the primitive actions together. Propositions and their connections are weighted by confidence, and updated by action executions. A re- active control of the task execution is achieved by an efficient algorithm, which is discussed and presented in detail, both formally and on a running example.

This paper proposes an approach for designing and implementing an interpretation system for a multi-sensory perception machine. Integrating multiple heterogeneous recognition and perception processes seems useful to efficiently obtain a reliable interpretation of a real complex dynamic environment. After tackling the problems of modelling objects and sensors, we propose a generic multi-sensory recognition and fusion approach and then present how are controlled and organized the perception tasks through a flexible distributed architecture. The work is validated by experimental results in real situations

The authors propose an approach to generalize the hypothesis and test recognition paradigm for multisensory environments and fairly generic object models. Matching, prediction and localization procedures are based on a generic representation of feature accuracy. This generic approach performs fusion both at the numeric (geometric) and at the symbolic (recognition) levels. Its reliability is illustrated by several real-world examples demonstrating recognition of real objects in complex cluttered environments using four types of sensory data: contour images (two viewpoints), stereovision 3-D line segments, range 3-D faces, and color images.>