Experience-Based Planning Domains: A Framework for Robot Task Learning and Planning. .
abstract   bibtex   
Learning and deliberation are required to endow a robot with the capabilities to acquire knowledge, perform a variety of tasks and interactions, and adapt to open-ended environments. This paper presents the notion of experience-based planning domains (EBPDs) for task level learning and planning in robotics. EBPDs provide methods for a robot to: (i) obtain robot activity experiences from the robot's performance; (ii) conceptualize each experience to a task model called activity schema; and (iii) exploit the learned activity schemata to make plans in similar situations. Experiences are episodic descriptions of plan-based robot activities including environment perception, sequences of applied actions and achieved tasks. The conceptualization approach integrates different techniques including deductive generalization, abstraction, goal inference and feature extraction to learn activity schemata. A high-level task planner was developed to find a solution for a similar task by following an activity schema. The proposed approach is illustrated in a restaurant environment where a service robot learns how to carry out complex tasks.
@inproceeduings {icaps16-106,
  track={Robotics Track},
  title={Experience-Based Planning Domains: A Framework for Robot Task Learning and Planning},
  authors={Vahid Mokhtari, Luis Seabra Lopes, Armando Jose Pinho},
  abstract={Learning and deliberation are required to endow a robot with the capabilities to acquire knowledge, perform a variety of tasks and interactions, and adapt to open-ended environments. This paper presents the notion of experience-based planning domains (EBPDs) for task level learning and planning in robotics. EBPDs provide methods for a robot to: (i) obtain robot activity experiences from the robot's performance; (ii) conceptualize each experience to a task model called activity schema; and (iii) exploit the learned activity schemata to make plans in similar situations. Experiences are episodic descriptions of plan-based robot activities including environment perception, sequences of applied actions and achieved tasks. The conceptualization approach integrates different techniques including deductive generalization, abstraction, goal inference and feature extraction to learn activity schemata. A high-level task planner was developed to find a solution for a similar task by following an activity schema. The proposed approach is illustrated in a restaurant environment where a service robot learns how to carry out complex tasks.},
  keywords={planning domain representations for robotics applications,acquisition of planning models for robotics,learning action and task models,integrated planning and execution in robotic architectures,real-world planning applications for autonomous robots}
}

Downloads: 0