In this chapter Teleo-Reactive Executive (T-REX) is designed, developed, tested and deployed as an onboard adaptive control system that integrates artificial intelligence (AI)-based planning and probabilistic state estimation in a hybrid executive. Probabilistic state estimation integrates a number of science observations to produce a likelihood that the vehicle sensors perceive a feature of interest. Onboard planning and execution enable adaptation of navigation and instrument control based on the probability of having detected such a phenomenon. It further enables goal-directed commanding within the context of projected mission state and allows for replanning for off-nominal situations and opportunistic science events.

Chapter Contents:

• 9.1 Introduction
• 9.2 A motivating example
• 9.3 Key concepts in T-REX
• 9.3.1 Mission, goals, actions
• 9.3.2 Distributing decision processes: a conceptual view
• 9.3.3 Interleaving planning and execution
• 9.4 The T-REX execution cycle
• 9.4.1 Synchronization: maintaining reactor state
• 9.4.2 Deliberation: making the agent proactive
• 9.4.2.1 Definitions
• 9.4.2.2 Flexible constraint-based plan representation
• 9.4.3 Consistency in timely plan dispatch
• 9.5 Experimental results
• 9.5.1 Augmenting traditional surveys
• 9.5.2 Extending Lagrangian surveys
• 9.6 Conclusion
• Acknowledgements
• References

Inspec keywords: autonomous underwater vehicles; control system synthesis; probability; sensors; adaptive control; path planning; state estimation; mobile robots; inference mechanisms

Other keywords: onboard adaptive control system; T-REX; probabilistic state estimation; hybrid executive; instrument control; AI-based planning; controller design; vehicle sensors; offnominal situation replanning; projected mission state; onboard execution; inference partitioning; science observations; Teleo-Reactive EXecutive; onboard planning; artificial intelligence-based planning; AUV mission control; science event replanning; navigation adaptation; goal-directed commanding

Subjects: Marine system control; Mobile robots; Control system analysis and synthesis methods; Knowledge engineering techniques; Self-adjusting control systems; Spatial variables control; Other topics in statistics; Control engineering computing; Simulation, modelling and identification