Conference Paper

Bridging the Gap between Task Planning and Path Planning

Inst. of Robotics & Mechatronics, German Aerosp. Center DLR, Oberpfaffenhofen
DOI: 10.1109/IROS.2006.282087 Conference: Intelligent Robots and Systems, 2006 IEEE/RSJ International Conference on
Source: DLR

ABSTRACT Autonomous service robots have to recognize and interpret their environment to be able to interact with it. This paper focuses on service tasks such as serving a glass of water where a humanoid two-arm-system has to acquire an object from the scene. A task planner should be able to autonomously discern the necessary actions to solve the task. In the process, a path planner can be used to compute motion sequences to execute these actions. To plan trajectories, the path planner requires a pair of configurations, the start and the goal configuration of the robot, to be provided e.g. by a task planner. This paper proposes a method to autonomously find the goal configurations necessary to acquire objects from the scene and thus makes an attempt to bridge the gap between task planning and path planning. The method determines where to grasp an object by analyzing the scene and the influence of obstacles on the intended grasp location. For the case where the goal object can not be grasped due to obstructing obstacles, a solution is proposed

0 Bookmarks
 · 
83 Views
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Autonomous mobile robots such as planetary rover need task and path planning abilities in order to fulfill their assigned missions. Task planning is caracterized by a symbolic reasoning and aims at defining a sequence of actions which will be executed to achieve the goals of the mission. Path planning allows to find some ways in the environment to reach these goals and corresponds to a geometric reasoning. Coupling these two kinds of reasoning presents open issues such as the description of the environment and the consideration of geometrical constraints that must be verified in order to act and move. This paper adresses these issues by studying different ways to couple a symbolic and a geometric reasoning and by proposing a hybrid planning architecture allowing to solve problems in which a mobile robot has to act and move in the environment.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Planning a mission for a mobile robot involves the use of a symbolic and a geometric planner. The gap be- tween their internal representation of the environment is an open issue and current researches are conducted without unified formalisms and algorithms. In this pa- per, we propose to extend the classical planning formal- ism in order to model actions with geometric precon- ditions and we propose, develop and test a constraint satisfaction method based on non-linear programming that aims at defining a destination attitude for motion planning.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Mobile robots such as explorer rovers need task and path planning abilities in order to fulfill their assigned missions: path planning to plan their movements and task planning to plan their actions. The coupling between these two kinds of planning presents open issues such as the description of the environment and the consideration of geometric constraints that must be verified in order to act and move during an action. This paper addresses these issues by proposing an architecture in which a hierarchical task planner sends requests to a path planner in order to check the feasibility of actions. Requirements allowing the path planner to produce an answer are presented as well as the description of planning operators. Finally, we specify the mechanism and the communication language by which the task planner produces requests and takes into account answers.
    AIP Conference Proceedings. 06/2008; 1019(1):162-167.

Full-text (4 Sources)

Download
67 Downloads
Available from
May 20, 2014