Hierarchical Hybrid Planning in a Mobile Service Robot

  title={Hierarchical Hybrid Planning in a Mobile Service Robot},
  author={Sebastian Stock and Masoumeh Mansouri and Federico Pecora and Joachim Hertzberg},
  booktitle={Deutsche Jahrestagung f{\"u}r K{\"u}nstliche Intelligenz},
Planning with diverse knowledge, i.e., hybrid planning, is essential for robotic applications. However, powerful heuristics are needed to reason efficiently in the resulting large search spaces. HTN planning provides a means to reduce the search space; furthermore, meta-CSP search has shown promise in hybrid domains, both wrt. search and online plan adaptation. In this paper we combine the two approaches by implementing HTN-style task decomposition as a meta-constraint in a meta-CSP search… 

Hierarchische hybride Planung für mobile Roboter

This thesis presents the hierarchical hybrid planner CHIMP which combines the advantages of hierarchical planning and hybrid planning with different forms of knowledge as a MetaCSP [28, 104].

Spatio-Temporal Planning for a Reconfigurable Multi-Robot System

This approach combines the use of constraint-based satisfaction techniques with linear optimization to solve a multicommodity min-cost flow problem to deal with the transportation of immobile robotic systems.

Beyond the frontiers of timeline-based planning

This thesis focuses on timeline-based planning, aiming at solving some efficiency issues which inevitably raise as a consequence of the drop out of these restrictions, and aims at reducing the performance gap between the classical approach at planning and the timeline- based one.

RTPO: A Domain Knowledge Base for Robot Task Planning

The OWL (Web Ontology Language) is adopted to represent the knowledge in robot task planning and it is demonstrated that RTPO has good performance in scalability and responsiveness, and the robot can achieve given high-level tasks based on RTPo.

Autonomous Operation of a Reconfigurable Multi-Robot System for Planetary Space Missions

This thesis proposes a mission planning algorithm which permits to exploit the flexibility of reconfigurable multi-robot systems and suggests effective solutions which permit an exploitation of an increased level of flexibility in future robotics missions.

Lifted Heuristics for Timeline-Based Planning

A new heuristic strategy is proposed which, while maintaining the variables lifted, allows more accurate decisions and pave the way for a new type of heuristics which, at present, allow this kind of solvers a significant performance improvement.

Investigating Lifted Heuristics for Timeline-based Planning

This paper investigates the use of lifted heuristics, inspired by the more classical ones for the resolution of STRIPSlike problems, for the efficient resolution of timeline-based planning problems.

A Constraint-Based Approach for Hybrid Reasoning in Robotics

The quest of AI and Robotics researchers to realize fully AI-driven integrated robotic systems has not yet led to such realizations, in spite of great attainments in both research areas. This thesi

Constraint-based Methods for Human-aware Planning

As more robots and sensors are deployed in work and home environments, there is a growing need for these devices to act with some degree of autonomy to fulfill their purpose. Automated planning can

Dynamic hierarchical reactive controller synthesis

A modeling formalism and a synthesis algorithm that exploits this hierarchical structure for more scalable synthesis of reactive controller synthesis and a procedure to construct a dynamic controller for local game graphs over hierarchies are proposed.



Online task merging with a hierarchical hybrid task planner for mobile service robots

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.

More knowledge on the table: Planning with space, time and resources for robots

This work proposes a planner grounded on well-founded constraint-based calculi that adhere to the requirements of a useful model in a robotic context and is validated through several experiments on real and simulated robot platforms.

A Flexible ANML Actor and Planner in Robotics

FAPE (Flexible Acting and Planning Environment), to the authors' knowledge the first system integrating an ANML planner and actor is reported on, which presents how planning is performed and integrated with acting, and describes briefly the robotics experiments and reports on initial performances.

An interface for interleaved symbolic-geometric planning and backtracking

This paper presents a meaningful interface, and insights into a methodology for developing interwoven symbolic-geometric domains, and presents a prototype implementation of the combined system on a PR2 robot.

Constraint propagation on interval bounds for dealing with geometric backtracking

This paper uses intervals to represent geometric configurations, and constraint propagation techniques to shrink these intervals according to the geometric constraints of the problem, and reports experiments that show how the search space is reduced.

Hierarchical Planning in the Now

This paper outlines an approach to the integration of task planning and motion planning that has the following key properties: It is aggressively hierarchical, operates on detailed, continuous geometric representations and partial symbolic descriptions.

HTN Planning: Complexity and Expressivity

How the complexity of HTN planning varies with various conditions on the task networks is described.

Hierarchical task and motion planning in the now

In this paper we outline an approach to the integration of task planning and motion planning that has the following key properties: It is aggressively hierarchical; it makes choices and commits to

The ANML Language

The central and unique features of the ANML language are described and key parts of the translation to PDDL are sketched, with some increase in the number and complexity of operators and conditions.

Towards a General Theory of Action and Time