Plan Projection under the APPEAL Robot Control Architecture
نویسندگان
چکیده
The paper presents APPEAL, a three-layer mobile robot control Architecture for Projection-based Planning, Execution and Learning, with a focus on its execution layer. Besides task decomposition and failure recovery, it supports the projection of navigation plans based on learned models of navigation actions. Plan projection is applied to detect opportunities for improving the robot’s navigation plan and transforming it accordingly. In the experimental section, we quantify the performance gains achieved by applying these techniques, both in simulation and on a robot. The savings are considerable.
منابع مشابه
Plan projection, execution, and learning for mobile robot control
Most state-of-the-art hybrid control systems for mobile robots are decomposed into different layers. While the deliberation layer reasons about the actions required for the robot in order to achieve a given goal, the behavioral layer is designed to enable the robot to quickly react to unforeseen events. This decomposition guarantees a safe operation even in the presence of unforeseen and dynami...
متن کاملIntegrating Reaction Plans and Layered Competences Through Synchronous Control
This paper describes an agent architecture and its implementation for situated robot control in field environments. The architecture draws from the ideas of universal plans and subsumption's layered control, producing reaction plans that exploit low-level competences as operators. The architecture has been implemented in an extended version of the GAPPS/Rex situated automata programming languag...
متن کاملOn-Line Execution of cc-Golog Plans
Previously, the plan language cc-Golog was introduced for the purpose of specifying event-driven behavior typically found in robot controllers. So far, however, cc-Golog is usable only for projecting the outcome of a plan and it is unclear how to actually execute plans on-line on a robot. In this paper, we provide such an execution model for ccGolog and, in addition, show how to interleave exec...
متن کاملFlexible Foot/Ankle Based on PKM with Force/Torque Sensor for Humanoid Robot
This paper describes the development of a novel humanoid robot foot/ankle based on an orientation Parallel Kinematic Mechanism for intelligent and flexible control. With three identical Universal-Prismatic-Spherical prismatic-actuated limbs and a central Universal-Revolute passive limb, the PKM can perform three degrees of freedom rotation motions. In order to enable the humanoid robot safely t...
متن کاملDesigning Path for Robot Arm Extensions Series with the Aim of Avoiding Obstruction with Recurring Neural Network
In this paper, recurrent neural network is used for path planning in the joint space of the robot with obstacle in the workspace of the robot. To design the neural network, first a performance index has been defined as sum of square of error tracking of final executor. Then, obstacle avoidance scheme is presented based on its space coordinate and its minimum distance between the obstacle and ea...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2003