Open-Source Online Mission-planning In Emergent Environments with PDDL for multi-robot applications

I. Michailidis, P. Michailidis, E. Kosmatopoulos, N. Bassiliades, “Open-Source Online Mission-planning In Emergent Environments with PDDL for multi-robot applications”, accepted for presentation at, 20th International Conference on Artificial Intelligence Applications and Innovations (AIAI 2024), 27 - 30 June 2024, Ionian University, Corfu, Greece.

Deliberative Agent, Replanning, Dynamic State Space, STRIPS, PDDL, State Graph Search, Object Collection, Autonomous Synergetic Vehicles

The current study focuses on the development of an open-source framework which is outsourcing the lack of expressivity of the standardized Planning Domain Definition Language – PDDL, leveraging the capacity and flexibility of the hosting environment in Python 3.8. The implementation was based on the definition and logic of a PDDL domain modeling an object stacking/collecting problem, in specified order and locations, by a fleet of autonomous synergetic vehicles by a centralized management agent. A PDDL-parser was utilized to instantiate the solver. Random changes were imposed in the fully-observable environment during mission execution. The proposed framework considered dynamic replanning of the currently valid mission, every time the state space – and consequently the corresponding state graph representation – is stochastically changed. Appropriate test scenarios were defined, to validate the capacity of the implemented framework and establish that it could serve as an interoperable and extensible foundation for other add-ons and graph-searching tools. The evidence from the simulation results indicates the speed and flexibility of the implemented environment for emulating the dynamic replanning problems in highly emergent scenario cases where the state space changes stochastically.