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

Abstract

Tasks that change the physical state of a robot take a considerable amount of time to execute. However, many robot applications spend the execution time waiting, although the following tasks might require time to prepare. This paper proposes to amend tasks with a description of their expected outcomes, which allows planning successive tasks based on this information. The suggested approach allows sequential and parallel composition of tasks, as well as reactive behavior modeled as state machines. The paper describes the means of modeling and executing these tasks, details different possibilities of planning in state machine tasks, and evaluates the benefits achievable using the approach.

Integrating planning and reactive behavior by using semantically annotated robot tasks

“…by checking that they control different devices. [1][2][3][4][5] A. Schierl, A. Hoffmann, L. Nägele, W. Reif Additionally, simple case distinctions can be made based on the possible ActivityResults, as shown in Fig. 14. A task with case distinction classifies the ActivityResults of the previous task and forwards them to the corresponding subtask depending on the decision condition.…”

“…18 shows a state machine of the three tasks (A), (B), and (C), switching from (A) to (C) if (A) succeeds, and to (B) if it fails. State (B) is always followed [1][2][3][4][5][6] A. Schierl, A. Hoffmann, L. Nägele, W. Reif ESC 2, 1 (2018) by (C), leading to two different paths reaching (C). Fig.…”

“…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.…”

Integrating planning and reactive behavior by using semantically annotated robot tasks

“…The work presented here is based on the conference paper on predictive preparation of state machine tasks 3 and extends it mainly in three fields:…”