Augmented Reactive Mission Planning Architecture

  • Somaiyeh MahmoudZadeh
  • David M. W. Powers
  • Reza Bairam Zadeh
Part of the Cognitive Science and Technology book series (CSAT)


Advancing the decision autonomy is a real challenge in the development of today AUVs as their operation is still restricted to very particular tasks that usually supervised by the human operator(s). Having a robust decision-making system along with an accurate motion planning mechanism facilitates a single vehicle to manage its restricted energy resources and endurance times toward accomplishing various complex tasks in a single mission while accompanying any immediate changes of a highly uncertain environment. The proceeding approach builds on recent two chapters towards developing a comprehensive structure for AUV mission planning, task-time managing, routing, and synchronic online motion planning adaptive to sudden changes of the time-variant marine environment. To this end, the following objectives are defined to approach the mentioned above expectations:
  • To augment the mission planner with a real time motion planner;

  • To accommodate a concurrent operation and synchronization among mission and motion planners;

  • To split a large-scaled terrain to smaller efficient operational windows, which results in reducing the computational burden of motion planning system;

  • To detect anomalies and compensate any lost time during the motion re-planning process;

  • Advancing the system with a synchronous re-scheduling mechanism to manage mission time and reprioritizing the tasks;

This chapter introduces an “Augmented Reactive Mission Planning Architecture” (ARMPA) and exercises DE meta-heuristic algorithm in layers of the proposed control architecture to investigate the efficiency of the structure in addressing the given objectives and ensuring the stability of ARMPA performance in real-time task-time-threat management. Numerical simulations for analysis of different situations of the real-world environment is accomplished separately for each layer and also for the entire ARMPA model at the end.

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Somaiyeh MahmoudZadeh
    • 1
  • David M. W. Powers
    • 2
  • Reza Bairam Zadeh
    • 3
  1. 1.Faculty of Information TechnologyMonash UniversityMelbourneAustralia
  2. 2.School of Computer Science, Engineering and MathematicsFlinders UniversityAdelaideAustralia
  3. 3.Fleet Space TechnologyAdelaideAustralia

Personalised recommendations