Automated Planning has been an active research topic for more than thi
rty years, but only recently has it started to move in the direction o
f combining planning and execution to achieve what is sometimes called
Intelligent Reactive Planning. We propose Simulation-Based planning a
s a new way to perform intelligent reactive planning. Simulation-Based
planning-unlike most other planning systems-integrates simulation int
o the planning process. Once a set of plans is generated, simulations
are used to test and evaluate the plans to choose the most applicable
plan for that current situation. In most planning systems, plan evalua
tion depends on rules alone, and because rules must be designed genera
l enough to cover all possible cases, the evaluation is not specific e
nough for some individual cases. However, when the plan evaluation is
done through simulations, the evaluation can be more fine-tuned to ind
ividual cases and can better allow better plans to be chosen for that
individual case. From the military planning perspective, the simulatio
n-based planner is also quite useful due to its ability to perform adv
ersarial and multi-agent planning. This is a natural consequence of us
ing simulation in the planning process. By allowing other entities suc
h as the enemy to simulate in parallel with the planner's forces, the
planner is able to observe, prior to the actual execution, the effects
of adversarial and multi-agent actions against its own plans.