scispace - formally typeset
Search or ask a question
Proceedings Article

Planning Domain + Execution Semantics: A Way Towards Robust Execution?

TL;DR: It is shown that the combined used of causal, temporal and categorical knowledge allows the robot to detect failures even when the effects of actions are not directly observable.
Abstract: Robots are expected to carry out complex plans in real world environments. This requires the robot to track the progress of plan execution and detect failures which may occur. Planners use very abstract world models to generate plans. Additional causal, temporal, categorical knowledge about the execution, which is not included in the planner's model, is often avail- able. Can we use this knowledge to increase robustness of execution and provide early failure detection? We propose to use a dedicated Execution Model to monitor the executed plan based on runtime observations and rich execution knowl- edge. We show that the combined used of causal, temporal and categorical knowledge allows the robot to detect failures even when the effects of actions are not directly observable. A dedicated Execution model also introduces a degree of mod- ularity, since the platform- and execution-specific knowledge does not need to be encoded into the planner.

Content maybe subject to copyright    Report

Citations
More filters
Journal ArticleDOI
TL;DR: Problem in different research areas related to mobile manipulation from the cognitive perspective are outlined, recently published works and the state-of-the-art approaches to address these problems are reviewed, and open problems to be solved are discussed.
Abstract: Service robots are expected to play an important role in our daily lives as our companions in home and work environments in the near future. An important requirement for fulfilling this expectation is to equip robots with skills to perform everyday manipulation tasks, the success of which is crucial for most home chores, such as cooking, cleaning, and shopping. Robots have been used successfully for manipulation tasks in wellstructured and controlled factory environments for decades. Designing skills for robots working in uncontrolled human environments raises many potential challenges in various subdisciplines, such as computer vision, automated planning, and human-robot interaction. In spite of the recent progress in these fields, there are still challenges to tackle. This article outlines problems in different research areas related to mobile manipulation from the cognitive perspective, reviews recently published works and the state-of-the-art approaches to address these problems, and discusses open problems to be solved to realize robot assistants that can be used in manipulation tasks in unstructured human environments.

43 citations

Proceedings ArticleDOI
17 Dec 2015
TL;DR: The planner CHIMP is introduced, which is based on meta-CSP planning to represent the hybrid plan space and uses hierarchical planning as the strategy for cutting efficiently through this space.
Abstract: Plan-based robot control has to consider a multitude of aspects of tasks at once, such as task dependency, time, space, and resource usage. Hybrid planning is a strategy for treating them jointly. However, by incorporating all these aspects into a hybrid planner, its search space is huge by construction. This paper introduces the planner CHIMP, which is based on meta-CSP planning to represent the hybrid plan space and uses hierarchical planning as the strategy for cutting efficiently through this space. The paper makes two contributions: First, it describes how HTN planning is integrated into meta-CSP reasoning leading to a planner that can reason about different forms of knowledge and that is fast enough to be used on a robot. Second, it demonstrates CHIMP's task merging capabilities, i.e., the unification of different tasks from different plan parts, resulting in plans that are more efficient to execute. It also allows to merge new tasks online into a plan that is being executed. This is demonstrated on a PR2 robot.

29 citations


Cites background from "Planning Domain + Execution Semanti..."

  • ...[24], which can benefit from CHIMP’s rich plan representation....

    [...]

Journal ArticleDOI
TL;DR: The general system architecture is introduced and some results in detail regarding hybrid reasoning and planning used in RACE are sketches, and instances of learning from the experiences of real robot task execution are sketched.
Abstract: This paper reports on the aims, the approach, and the results of the European project RACE. The project aim was to enhance the behavior of an autonomous robot by having the robot learn from conceptualized experiences of previous performance, based on initial models of the domain and its own actions in it. This paper introduces the general system architecture; it then sketches some results in detail regarding hybrid reasoning and planning used in RACE, and instances of learning from the experiences of real robot task execution. Enhancement of robot competence is operationalized in terms of performance quality and description length of the robot instructions, and such enhancement is shown to result from the RACE system.

29 citations


Cites background from "Planning Domain + Execution Semanti..."

  • ...As pointed out in [8], the planner’s knowledge and that of the semantic execution monitor need not overlap completely: some of it may be execution-specific for improving robustness and enabling early failure detection....

    [...]

Proceedings ArticleDOI
20 Oct 2014
TL;DR: The robot's ontology is extended with concepts for representing human-robot interactions as well as the experiences of the robot, and these experiences are extracted and stored in memory and they are used as input for learning methods.
Abstract: Intelligent service robots should be able to improve their knowledge from accumulated experiences through continuous interaction with the environment, and in particular with humans. A human user may guide the process of experience acquisition, teaching new concepts, or correcting insufficient or erroneous concepts through interaction. This paper reports on work towards interactive learning of objects and robot activities in an incremental and open-ended way. In particular, this paper addresses human-robot interaction and experience gathering. The robot's ontology is extended with concepts for representing human-robot interactions as well as the experiences of the robot. The human-robot interaction ontology includes not only instructor teaching activities but also robot activities to support appropriate feedback from the robot. Two simplified interfaces are implemented for the different types of instructions including the teach instruction, which triggers the robot to extract experiences. These experiences, both in the robot activity domain and in the perceptual domain, are extracted and stored in memory, and they are used as input for learning methods. The functionalities described above are completely integrated in a robot architecture, and are demonstrated in a PR2 robot.

27 citations

Journal ArticleDOI
TL;DR: An approach for scene understanding based on qualitative descriptors, domain knowledge and logics is proposed, and promising results were obtained.
Abstract: An approach for scene understanding based on qualitative descriptors, domain knowledge and logics is proposed in this paper. Qualitative descriptors, qualitative models of shape, colour, topology and location are used for describing any object in the scene. Two kinds of domain knowledge are provided: (i) categorizations of objects according to their qualitative descriptors, and (ii) semantics for describing the affordances, mobility and other functional properties of target objects. First order logics are obtained for reasoning and scene understanding. Tests were carried out at the Interact@Cartesium scenario and promising results were obtained.

26 citations

References
More filters
Proceedings Article
14 Jul 1991
TL;DR: This paper demonstrates how metric and Allenstyle constraint networks can be integrated in a constraint-based reasoning system and develops a simple but powerful logical language for expressing both quantitative and qualitative information.
Abstract: Research in Artificial Intelligence on constraint-based representations for temporal reasoning has largely concentrated on two kinds of formalisms: systems of simple linear inequalities to encode metric relations between time points, and systems of binary constraints in Allen's temporal calculus to encode qualitative relations between time intervals. Each formalism has certain advantages. Linear inequalities can represent dates, durations, and other quantitive information; Allen's qualitative calculus can express relations between time intervals, such as disjointedness, that are useful for constraint-based approaches to planning. In this paper we demonstrate how metric and Allenstyle constraint networks can be integrated in a constraint-based reasoning system. The highlights of the work include a simple but powerful logical language for expressing both quantitative and qualitative information; translation algorithms between the metric and Allen sublanguages that entail minimal loss of information; and a constraint-propagation procedure for problems expressed in a combination of metric and Allen constraints.

225 citations


"Planning Domain + Execution Semanti..." refers background in this paper

  • ...Note that metric bounds can be added without loosing tractability (Kautz and Ladkin 1991)....

    [...]

Journal ArticleDOI
TL;DR: This article provides the final step in the classification of complexity for satisfiability problems over constraints expressed in Allen's interval algebra, and shows that this algebra contains exactly eighteen maximal tractable subalgebras, and reasoning in any fragment not entirely contained in one of these subalagbras is NP-complete.
Abstract: Allen's interval algebra is one of the best established formalisms for temporal reasoning. This article provides the final step in the classification of complexity for satisfiability problems over constraints expressed in this algebra. When the constraints are chosen from the full Allen's algebra, this form of satisfiability problem is known to be NP-complete. However, eighteen tractable subalgebras have previously been identified; we show here that these subalgebras include all possible tractable subsets of Allen's algebra. In other words, we show that this algebra contains exactly eighteen maximal tractable subalgebras, and reasoning in any fragment not entirely contained in one of these subalgebras is NP-complete. We obtain this dichotomy result by giving a new uniform description of the known maximal tractable subalgebras, and then systematically using a general algebraic technique for identifying maximal subalgebras with a given property.

162 citations


"Planning Domain + Execution Semanti..." refers methods in this paper

  • ...In order to have tractable reasoning upon temporal constraints, we use convex IA relations (Vilain and Kautz 1986; Krokhin, Jeavons, and Jonsson 2003)....

    [...]

Journal Article
TL;DR: The timeline-based approach to planning represents an effective alternative to classical planning for complex domains requiring the use of both temporal reasoning and scheduling features.
Abstract: The timeline-based approach to planning represents an effective alternative to classical planning for complex domains requiring the use of both temporal reasoning and scheduling features This pape

92 citations


"Planning Domain + Execution Semanti..." refers background in this paper

  • ...In temporal planning and scheduling (Gallien, Ingrand, and Lemai 2004; Fratini, Pecora, and Cesta 2008; Barreiro et al. 2012; Di Rocco, Pecora, and Saffiotti 2013) temporal and resource knowledge about execution is used to detect failure....

    [...]

Proceedings Article
13 Jul 2008
TL;DR: The novelty of this approach is in integrating deliberation and reaction over different temporal and functional scopes within a single model, and in breaking new ground in oceanography by allowing for precise sampling within a feature of interest using an autonomous robot.
Abstract: We describe a novel integration of Planning with Probabilistic State Estimation and Execution. The resulting system is a unified representational and computational framework based on declarative models and constraint-based temporal plans. The work is motivated by the need to explore the oceans more cost-effectively through the use of Autonomous Underwater Vehicles (AUV), requiring them to be goal-directed, perceptive, adaptive and robust in the context of dynamic and uncertain conditions. The novelty of our approach is in integrating deliberation and reaction over different temporal and functional scopes within a single model, and in breaking new ground in oceanography by allowing for precise sampling within a feature of interest using an autonomous robot. The system is general-purpose and adaptable to other ocean going and terrestrial platforms.

84 citations


"Planning Domain + Execution Semanti..." refers background in this paper

  • ...One well known architecture for continuous planning is TRex (McGann et al. 2008), which is based on a hierarchical network of so-called reactors, each of which monitors a task at a different level of abstraction....

    [...]

ReportDOI
Richard Fikes1
01 Apr 1971
TL;DR: PANEXl, a plan executor for the Stanford Research Institute robot system, is described, designed so that it executes only that portion of the plan necessary for completing the task, reexecutes any portion ofThe plan that has failed to achieve the desired results, and initiates replanning in situations where the plan can no longer be effective in completing thetask.
Abstract: We describe PLANEX1, a plan executor for the Stanford Research Institute robot system. The problem-solving program STRIPS creates a plan consisting of a sequence of actions, and PLANEX1 program carries out the plan by executing the actions. PLANEX1 is designed so that it executes only that portion of the plan necessary for completing the task, reexecutes any portion of the plan that has failed to achieve the desired results, and initiates replanning in situations where the plan can no longer be effective in completing the task. The scenario for an example plan execution is given.

69 citations


"Planning Domain + Execution Semanti..." refers background in this paper

  • ...PLANEX converts a STRIPS plan into a tabular structure (triangle table) which captures the causal dependencies (preconditions-action-effects)....

    [...]

  • ...Therefore, PLANEX requires direct observability of effects....

    [...]

  • ...The first attempt to explicitly represent knowledge used for Execution Monitoring was PLANEX (Fikes 1971)....

    [...]