Search

Synthesizing plans for a deformable object to transit from initial observations to goal observations, both of which are represented by high-dimensional data (namely “raw” data), is challenging due to the difficulty of learning abstract state representations of raw data and transition models of continuous states and continuous actions. Even though there have been some approaches making remarkable progress regarding the planning problem, they often neglect actions between observations and are unable to generate action sequences from initial observations to goal observations. In this paper, we propose a novel algorithm framework, namely AGN. We first learn a state-abstractor model to abstract states from raw observations, a state-generator model to generate raw observations from states, a heuristic model to predict actions to be executed in current states, and a transition model to transform current states to next states after executing specific actions. After that, we directly generate plans for a deformable object by performing the four models. We evaluate our approach in continuous domains and show that our approach is effective with comparison to state-of-the-art algorithms.

In the last decade, many approaches to automated service composition have been proposed. However, most of them do not fully exploit the opportunities offered by the Internet of Services (IoS). In this article, we focus on the dynamicity of the execution environment, that is, any change occurring at run-time that might affect the system, such as changes in service availability, service behavior, or characteristics of the execution context. We indicate that any IoS-based application strongly requires a composition framework that supports for the automation of all the phases of the composition life cycle, from requirements derivation, to synthesis, deployment and execution. Our solution to this ambitious problem is an AI planning-based composition framework that features abstract composition requirements and context-awareness. In the proposed approach most human-dependent tasks can be accomplished at design time and the few human intervention required at run time do not affect the system execution. To demonstrate our approach in action and evaluate it, we exploit the ASTRO-CAptEvo framework, simulating the operation of a fully automated IoS-based car logistics scenario in the Bremerhaven harbor.

This paper describes an algorithm for semantic decomposition. For that we surveys languages used to enrich contextual information with semantic descriptions. Such descriptions can be e.g. applied to enable reasoning when collecting vast amounts of information. In particular, we focus on the elements of the languages that make up their semantic. To do so, we compare the expressiveness of the well-known languages OWL, PDDL and MOF with a theory from linguistic called the Natural Semantic Metalanguage. We then analyze how the semantic of the language is build up and describe how semantic decomposition based on the semantic primes can be used for a so called mental lexicon. This mental lexicon can be used to reason upon semantic service description in the research domain of service match making.

International audience; Automated composition of Web services or the process of forming new value-added Web services is one of the most promising challenges facing the Semantic Web today. Semantics enables Web service to describe capabilities together with their processes, hence one of the key elements for the automated composition of Web services. In this paper, we focus on the functional level of Web services i.e. services are described according to some input, output parameters semantically enhanced by concepts in a domain ontology. Web service composition is then viewed as a composition of semantic links wherein the latter links refer to semantic matchmaking between Web service parameters (i.e. outputs and inputs) in order to model their connection and interaction. The key idea is that the matchmaking enables, at run time, finding semantic compatibilities among independently defined Web service descriptions. By considering such a level of composition, a formal model to perform the automated composition of Web services i.e. Semantic Link Matrix, is introduced. The latter model is required as a starting point to apply problem-solving techniques such as regression (or progression)-based search for Web service composition. The model supports a semantic context in order to find correct, complete, consistent and robust plans as solutions. In this paper, an innovative and formal model for an AI (Artificial Intelligence) planning-oriented composition is presented. Our system is implemented and interacting with Web services which are dedicated to Telecom scenarios. The preliminary evaluation results showed high efficiency and effectiveness of the proposed approach. Read More: http://www.worldscientific.com/doi/abs/10.1142/S0218843009001975

This paper presents a new approach to plan high-level manipulation actions for cleaning surfaces in household environments, like removing dirt from a table using a rag. Dragging actions can change the distribution of dirt in an unpredictable manner, and thus the planning becomes challenging. We propose to define the problem using explicitly uncertain actions, and then plan the most effective sequence of actions in terms of time. However, some issues have to be tackled to plan efficiently with stochastic actions. States become hard to predict after executing a few actions, so replanning every few actions with newer perceptions gives the best results, and the trade-off between planning time and plan quality is also important. Finally a learner is integrated to provide adaptation to changes, such as different rag grasps, robots, or cleaning surfaces. We demonstrate experimentally, using two different robot platforms, that planning is more advantageous than simple reactive strategies for accomplishing complex tasks, while still providing a similar performance for easy tasks. We also performed experiments where the rag grasp was changed, and thus the behaviour of the dragging actions, showing that the learning capabilities allow the robot to double its performance with a new rag grasp after a few cleaning iterations., This work was supported by EU Project IntellActFP7-ICT2009-6-269959 and by the Spanish Ministry of Science and Innovation under project PAU+ DPI2011-27510. D. Martínez is also supported by the Spanish Ministry of Education, Culture and Sport via a FPU doctoral grant (FPU12-04173).

A reinforcement learning agent that autonomously explores its environment can utilize a curiosity drive to enable continual learning of skills, in the absence of any external rewards. We formulate curiosity-driven exploration, and eventual skill acquisition, as a selective sampling problem. Each environment setting provides the agent with a stream of instances. An instance is a sensory observation that, when queried, causes an outcome that the agent is trying to predict. After an instance is observed, a query condition, derived herein, tells whether its outcome is statistically known or unknown to the agent, based on the confidence interval of an online linear classifier. Upon encountering the first unknown instance, the agent "queries'' the environment to observe the outcome, which is expected to improve its confidence in the corresponding predictor. If the environment is in a setting where all instances are known, the agent generates a plan of actions to reach a new setting, where an unknown instance is likely to be encountered. The desired setting is a self-generated goal, and the plan of action, essentially a program to solve a problem, is a skill. The success of the plan depends on the quality of the agent's predictors, which are improved as mentioned above. For validation, this method is applied to both a simulated and real Katana robot arm in its "blocks-world'' environment. Results show that the proposed method generates sample-efficient curious exploration behavior, which exhibits developmental stages, continual learning, and skill acquisition, in an intrinsically-motivated playful agent.

In this paper we present the idea that by using AI planning in concert with formal task modeling, the overhead associated with plan creation for complex tasks can be reduced. The proposed approach uses a SysML taxonomy to model the system capabilities and the process specification, and the PDDL planning language to determine acceptable objective solutions. This idea is applied to the manufacturing domain, and examples are shown modeling a multi-robot system in an automobile manufacturing environment. A discussion is given regarding the merits of the demonstrated approach.

International audience; Most real-world Planning problems are multi-objective, trying to minimize both the makespan of the solution plan, and some cost of the actions involved in the plan. But most, if not all existing approaches are based on single-objective planners, and use an aggregation of the objectives to remain in the single-objective context. Divide and Evolve (DaE) is an evolutionary planner that won the temporal deterministic satisficing track at the last International Planning Competitions (IPC). Like all Evolutionary Algorithms (EA), it can easily be turned into a Pareto-based Multi-Objective EA. It is however important to validate the resulting algorithm by comparing it with the aggregation approach: this is the goal of this paper. The comparative experiments on a recently proposed benchmark set that are reported here demonstrate the usefulness of going Pareto-based in AI Planning.

All standard AI planners to-date can only handle a single objective, and the only way for them to take into account multiple objectives is by aggregation of the objectives. Furthermore, and in deep contrast with the single objective case, there exists no benchmark problems on which to test the algorithms for multi-objective planning. Divide and Evolve (DAE) is an evolutionary planner that won the (single-objective) deterministic temporal satisficing track in the last International Planning Competition. Even though it uses intensively the classical (and hence single-objective) planner YAHSP, it is possible to turn DAE-YAHSP into a multi-objective evolutionary planner. A tunable benchmark suite for multi-objective planning is first proposed, and the performances of several variants of multi-objective DAE-YAHSP are compared on different instances of this benchmark, hopefully paving the road to further multi-objective competitions in AI planning., 7th International Conference on Evolutionary Multi-Criterion Optimization (2013) To appearr. arXiv admin note: text overlap with arXiv:0804.3965 by other authors

Energy-saving offices require autonomous and optimised control of integrated devices and appliances with the objective of saving energy while the occupant comfort and productivity are preserved. We propose an approach that analyses and controls an office space and accounts for the objectives of energy-saving offices. The approach considers ontology-based occupant activity recognition using simple sensors to process the context information, and employs Artificial Intelligence planning to control appliances. The approach is evaluated in a semi-simulated setting. The activity recognition strategy is tested in an actual living lab and shows recognising accuracy of about 80%. The planning technique is able to cope efficiently under a simulated and increasing number of offices and recognised activities. The overall solution shows intriguing potential for energy saving in the order of 70%, given mostly sunny days and a provisional set of devices for experimentation.

Automated services composition is an active research area nowadays. The application of this technology to specific domains, as well as the use of basic Telecommunications services such as call or SMS, offers new challenges. This paper presents the main components of an architecture for automated composition for Environmental Management. The proposed architecture uses Natural Language processing and AI Planners techniques domains. Although the present architecture is focused in a particular domain, most of the principles discussed here are applicable to similar scenarios.

e-Tourism is a tourist recommendation and planning application to assist users on the organization of a leisure and tourist agenda. First, a recommender system offers the user a list of the city places that are likely of interest to the user. This list takes into account the user demographic classification, the user likes in former trips and the preferences for the current visit. Second, a planning module schedules the list of recommended places according to their temporal characteristics as well as the user restrictions; that is the planning system determines how and when to realize the recommended activities. Having the list of recommended activities organized as an agenda (i.e. an executable plan), is a relevant characteristic that most recommender systems lack., This work has been partially funded by Consolider Ingenio 2010 CSD2007-00022 project, by the Spanish Government MICINN TIN2008-6701-C03-01 project and by the Valencian Government GVPRE/2008/384 project. We thank J. Benton for having provided us with the system Sapa to execute our experiments.

This paper presents the planning system Pdk (Planning with Domain Knowledge), based on the translation of planning problems into Linear Time Logic theories, in such a way that finding solution plans is reduced to model search. The model search mechanism is based on temporal tableaux. The planning language accepted by the system allows one to specify extra problem dependent information, that can be of help both in reducing the search space and finding plans of better quality.

The sewer inspection robot MAKRO is an autonomous multi-segment robot with worm-like shape driven by wheels. It is currently under development in the project MAKRO-PLUS. The robot has to navigate autonomously within sewer systems. Its first tasks will be to take water probes, analyze it onboard, and measure positions of manholes and pipes to detect polluted-loaded sewage and to improve current maps of sewer systems. One of the challenging problems is the controller software, which should enable the robot to navigate in the sewer system and perform the inspection tasks autonomously, not inflicting any self-damage. This paper focuses on the route planning and replanning aspect of the robot. The robot's software has four different levels, of which the planning system is the highest level, and the remaining three are controller levels each with a different degree of abstraction. The planner coordinates the sequence of actions that are to be successively executed by the robot.

International audience; We present an any-time concurrent probabilistic temporal planner (CPTP) that includes continuous and discrete uncertainties and metric functions. Rather than relying on dynamic programming our approach builds on methods from stochastic local policy search. That is, we optimise a parameterised policy using gradient ascent. The flexibility of this policy-gradient approach, combined with its low memory use, the use of function approximation methods and factorisation of the policy, allow us to tackle complex domains. This Factored Policy Gradient (FPG) planner can optimise steps to goal, the probability of success, or attempt a combination of both. We compare the FPG planner to other planners on CPTP domains, and on simpler but better studied non-concurrent non-temporal probabilistic planning (PP) domains. We present FPG-ipc, the PP version of the planner which has been successful in the probabilistic track of the fifth international planning competition.

An action is redundant in a planning domain if it is not needed to reach the goal. In this paper, we study the computational complexity of some problems related to the redundancy of actions: checking whether a domain contains a redundant action, what is the minimal number of actions needed to make the goal reachable, checking whether the removal of an action does not increase the minimal plan length, etc.