Decision making in a real-world domain like logistics is challenging for an autonomous technical system like a software agent. In this paper the problem of planning in such an environment is addressed. Classical planning and probabilistic criteria-directed scheduling components are tied together by a metalevel control and supplemented by a sophisticated world model and a risk management module to form a plan-based decision support system for autonomous control of logistic entities. The system is designed to be integrated in a multi-agent based simulation for evaluation and will later be used to support autonoumous decision making in real-world logistic domains.