Preview coordination: An enhanced execution model for online scheduling of mobile manipulation tasks

Abstract

Abstract-Task specification models define the activities to be executed by a robot in order to achieve its goal. Classical examples are the sequences involved in assembly or pick and place tasks. This work introduces the preview coordination execution model, an extension to the traditional way in which the execution of such task specifications is coordinated at runtime. Instead of taking activities one-by-one as defined in the task specification model, preview coordination optimizes the task scheduling based on knowledge about the likelihood that not just the activities required by the current state can be executed, but that also one or more of those related to future states of the system can be activated. An experiment with mobile manipulation tasks illustrates the benefits of preview coordination.

Integrating planning and reactive behavior by using semantically annotated robot tasks

“…Still, this paper is limited to simple preparation strategies of state machines (transitions can be guaranteed, or planned when the state is entered). As a part of further research, more complex strategies might benefit from likelihood annotations 7 or estimated preparation times to decide which transitions in the state machine will likely happen and should be prepared first (to reduce the risk of missed transitions). Additionally, longer sequences of transitions could be prepared in corresponding situations, e.g.…”

“…As an extension to rFSM state machines, Scioni et al describe how to achieve preview coordination 7 : In this approach, the execution environment takes hints about execution probabilities based on likelihood labels on some transitions. Using these labels, likely successor states can be prepared (performing some of their work) while the previous state is still active, as long as there is no conflict between the preparation steps and the actions performed in the current state.…”

Integrating Reactive Behavior and Planning: Optimizing Execution Time Through Predictive Preparation of State Machine Tasks

“…Still, this paper is limited to simple preparation strategies of state machines (transitions can be guaranteed, or planned when the state is entered). As a part of further research, more complex strategies might benefit from likelihood annotations [6] or estimated planning times to decide which transitions in the state machine will likely happen and should be prepared first (to reduce the risk of missed transitions). Additionally, longer sequences of transitions could be prepared in corresponding situations, e.g.…”

“…As an extension to rFSM state machines, Scioni et al [6] describe how to achieve preview coordination: In this approach, the execution environment takes hints about ex-ecution probabilities based on likelihood labels on some transitions. Using these labels, likely successor states can be prepared (performing some of their work) while the previous state is still active, as long as there is no conflict between the preparation steps and the actions performed in the current state.…”

Integrating planning and reactive behavior by using semantically annotated robot tasks

“…16, guaranteeing that every transition can be taken immediately. For [1][2][3][4][5][6][7] execution, all traces through this state machine have to be prepared beforehand, so preparation looks like the one shown for the complex composition in Fig. 17.…”