Probabilistic, Prediction-Based Schedule Debugging for Autonomous Robot Office Couriers
KI '99 Proceedings of the 23rd Annual German Conference on Artificial Intelligence: Advances in Artificial Intelligence
Concurrent reactive plans: anticipating and forestalling execution failures
Concurrent reactive plans: anticipating and forestalling execution failures
Hi-index | 0.00 |
Temporal projection is a crucial task in planning. In order to achieve its goals, the planner must be able to reason about the consequences of its actions. In the real world, the planner does not have complete information about the environment or even the consequences of its actions. The planner thus must be able to reason about the probabilistic nature of the world and the probabilistic effects of its action. .pp Interactions between actions and events in the world are not only probabilistic; they also are temporally complex. Simultaneous events can interact in many different ways depending on their temporal properties. An action''s temporal relation to its preconditions and effects can also become quite complex. .pp Existing projection systems are weak in their representations of temporally complex actions and events in a probabilistic world. Those that can handle probabilistic situations have a limited representation of temporal relations, while those that can handle complex temporal relations generally assume the world to be completely deterministic. Moreover, the speed of existing probabilistic projection systems are low. These systems are impractical to scale up to larger problems. In this thesis, we propose a practical projection system that can handle both the probabilistic nature of the world and the temporally complex nature of actions. The projection is based on simulation methods. Projection is done by simulating possible courses of events, one at a time. The simulation traces are then collected and processed by a projection module front-end, which provides the planner and the execution monitor with probabilistic estimates of propositions'' values. The representation allowed by the system is rich in both the temporal and the probabilistic aspects.