A practical framework for robust decision-theoretic planning and execution for service robots. .
abstract   bibtex   
The deployment of robots in populated environments is recently gaining more interest because of increased maturity and capability of this technology. In this context, sophisticated planning techniques are required because there is a need of increasing the complexity of the tasks that the robot can accomplish. In this paper, we present a practical framework for generation and execution of robust plans for service robots. The proposed framework is particularly suitable for service robots involved in situations where perception noise determines action failures and user interaction introduces uncertainty in the task to be executed. More specifically, our framework integrates several formalisms to: (i) compactly represent complex tasks using Progressive reasoning units (PRUs); (ii) support perception noise, uncertainty of the outcomes using decision-theoretic planning techniques based on Markov Decision process (MDP) to derive a policy of complex task execution; and (iii) support execution failures by transforming the policy into a Petri-Net Plan (PNP) to have robust execution plans.
@inproceeduings {icaps16-140,
  track={Robotics Track},
  title={A practical framework for robust decision-theoretic planning and execution for service robots},
  authors={Luca Iocchi, Laurent Jeanpierre, Mar�a T. L�zaro, Mouaddib Abdel-Illah},
  abstract={The deployment of robots in populated environments is recently gaining more interest because of increased maturity and capability of this technology. In this context, sophisticated planning techniques are required because there is a need of increasing the complexity of the tasks that the robot can accomplish.
In this paper, we present a practical framework for generation and execution of robust plans for service robots. The proposed framework is particularly suitable
for service robots involved in situations where perception noise determines action failures and user interaction introduces uncertainty in the task to be executed.
More specifically, our framework integrates several formalisms to: (i) compactly represent complex tasks using Progressive reasoning units (PRUs); (ii) support perception noise, uncertainty of the outcomes using decision-theoretic planning techniques based on Markov Decision process (MDP) to derive a policy of complex task execution; and (iii) support execution failures by transforming the policy into a Petri-Net Plan (PNP) to have robust execution plans.},
  keywords={robot motion; path; task and mission planning and execution,planning domain representations for robotics applications,human-aware planning and execution in human-robot interaction; including safety}
}

Downloads: 0