This paper presents an approach to knowledge-based inspection planning for solid objects. The goals of intelligent inspection planning include determining (i) which entities (edge segments, etc) of the object should be measured, (ii) what camera locations and viewing directions should be used to perform inspection, and (Hi) how can the search for these entities, and their inspection be robustly and efficiently done once the sensor data is obtained. An effective solution to this problem is clearly very important not only from the automation point of view, but also in order to effectively gather and use sensor information to overcome the volume and complexity of required information for adequate performance. In order to achieve the inspection planning goals, several interrelated problems must be solved. These problems include: (i) developing hierarchical representation mechanisms to effectively capture the knowledge about geometric entities, their relationships, sensors, and plans, (ii) reasoning mechanisms to determine the different attributes of the different features of object to be inspected, and the alternative strategies which can be used for inspection of each attribute, (Hi) strategies for setting the sensor parameters, such as the position and viewing direction of the cameras, and methods to determine the visible entities in each configuration, and (iv) plan optimization. Our prototype is developed in the Smalltalk object oriented environment.