Task Planning for an Autonomous Service Robot

Keller, Thomas; Eyerich, Patrick; Nebel, Bernhard

doi:10.1007/978-3-642-16111-7_41

Cited by 6 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The planning system of DESIRE project [4] was for an autonomous robot capable of performing service tasks in a typical kitchen environment. They dealt with world environments by performing a continuous loop between planning, plan execution and execution monitoring.…”

Section: Related Workmentioning

confidence: 99%

Interactive symbol generation of task planning for daily assistive robot

Mikita

Azuma

Kakiuchi

et al. 2012

2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012)

View full text Add to dashboard Cite

For the development of both hardware and software, task plannings become more and more important for robots to perform various tasks. Applying task planning to robotic system for working in real environments has difficulties. Estimating required symbols before planning is difficult because real environments are partially observable. In this paper, we proposed a method for task planning in partially observable environments with unknown objects. To construct conditional plans used in these environments, we extend the description of actions to multi-effect actions, and to deal with unknown objects, robots get new symbols generated by human interaction on demand. Additionally we show experiments of Willow Garage's PR2 executing the task in the real environment with unknown objects.

show abstract

Section: Related Workmentioning

confidence: 99%

Interactive symbol generation of task planning for daily assistive robot

Mikita

Azuma

Kakiuchi

et al. 2012

2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012)

View full text Add to dashboard Cite

show abstract

“…Following similar arguments, Nebel et al [18] and Keller et. al [12] demonstrate how a classical planner embedded in a continual planning loop solves complex mobile manipulation tasks on a robot. Replanning is used to deal with execution failures and unexpected situations.…”

Section: Related Workmentioning

confidence: 99%

An Experimental Comparison of Classical, FOND and Probabilistic Planning

Hertle

Dornhege

Keller

et al. 2014

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Domain-independent planning in general is broadly applicable to a wide range of tasks. Many formalisms exist that allow the description of different aspects of realistic problems. Which one to use is often no obvious choice, since a higher degree of expressiveness usually comes with an increased planning time and/or a decreased policy quality. Under the assumption that hard guarantees are not required, users are faced with a decision between multiple approaches. As a generic model we use a probabilistic description in the form of Markov Decision Processes (MDPs). We define abstracting translations into a classical planning formalism and fully observable nondeterministic planning. Our goal is to give insight into how stateof-the-art systems perform on different MDP planning domains.

show abstract

“…Nourbakhsh [1998] also describes a hierarchical approach to interleaving planning and execution that is similar to ours, but which does not integrate geometric reasoning. Keller et al [2010] outline a planning and execution system that is in spirit very similar to ours, using the planning method described by Dornhege et al [2009]. Uncertainty is handled with online execution monitoring and replanning, including the ability to postpone making plans until sufficient information is available.…”

Section: Integrating Logical and Geometric Planningmentioning

confidence: 99%

Integrated Robot Task and Motion Planning in the Now

Kaelbling¹,

Lozano-Pérez

2012

View full text Add to dashboard Cite

Public reporting burden for the collection of information is estimated to average 1 hour per response, including the time for reviewing instructions, searching existing data sources, gathering and maintaining the data needed, and completing and reviewing the collection of information. Send comments regarding this burden estimate or any other aspect of this collection of information, including suggestions for reducing this burden, to Washington Headquarters Services, Directorate for Information Operations and Reports, 1215 Jefferson Davis Highway, Suite 1204, Arlington VA 22202-4302. Respondents should be aware that notwithstanding any other provision of law, no person shall be subject to a penalty for failing to comply with a collection of information if it does not display a currently valid OMB control number. This paper provides an approach to integrating geometric motion planning with logical task planning for long-horizon tasks in domains with many objects. We propose a tight integration between the logical and geometric aspects of planning. We use a logical representation which includes entities that refer to poses, grasps, paths and regions, without the need for a priori discretization. Given this representation and some simple mechanisms for geometric inference,we characterize the pre-conditions and effects of robot actions in terms of these logical entities. We then reason about the interaction of the geometric and non-geometric aspects of our domains using the general-purpose mechanism of goal regression (also known as pre-image backchaining). We propose an aggressive mechanism for temporal hierarchical decomposition, which postpones the pre-conditions of actions to create an abstraction hierarchy that both limits the lengths of plans that need to be generated and limits the set of objects relevant to each plan. We describe an implementation of this planning method and demonstrate it in a simulated kitchen environment in which it solves problems that require approximately 100 individual pick or place operations for moving multiple objects in a complex domain. This paper provides an approach to integrating geometric motion planning with logical task planning for long-horizon tasks in domains with many objects. We propose a tight integration between the logical and geometric aspects of planning. We use a logical representation which includes entities that refer to poses, grasps, paths and regions, without the need for a priori discretization. Given this representation and some simple mechanisms for geometric inference, we characterize the pre-conditions and effects of robot actions in terms of these logical entities.We then reason about the interaction of the geometric and non-geometric aspects of our domains using the general-purpose mechanism of goal regression (also known as pre-image backchaining). We propose an aggressive mechanism for temporal hierarchical decomposition, which postpones the pre-conditions of actions to create an abstraction hierarchy that both limits the lengths of plans that need t...

show abstract

Task Planning for an Autonomous Service Robot

Cited by 6 publications

References 7 publications

Interactive symbol generation of task planning for daily assistive robot

Interactive symbol generation of task planning for daily assistive robot

An Experimental Comparison of Classical, FOND and Probabilistic Planning

Integrated Robot Task and Motion Planning in the Now

Contact Info

Product

Resources

About