Summary: Autonomous robots that are to perform complex everyday tasks such as making pancakes have to understand how the effects of an action depend on the way the action is executed. Within Artificial Intelligence, classical planning reasons about whether actions are executable, but makes the assumption that the actions will succeed (with some probability). In this work, we have designed, implemented, and analyzed a framework that allows us to envision the physical effects of robot manipulation actions. We consider envisioning to be a qualitative reasoning method that reasons about actions and their effects based on simulation-based projections. Thereby it allows a robot to infer what could happen when it performs a task in a certain way. This is achieved by translating a qualitative physics problem into a parameterized simulation problem; performing a detailed physics-based simulation of a robot plan; logging the state evolution into appropriate data structures; and then translating these sub-symbolic data structures into interval-based first-order symbolic, qualitative representations, called timelines. The result of the envisioning is a set of detailed narratives represented by timelines which are then used to infer answers to qualitative reasoning problems. By envisioning the outcome of actions before committing to them, a robot is able to reason about physical phenomena and can therefore prevent itself from ending up in unwanted situations. Using this approach, robots can perform manipulation tasks more efficiently, robustly, and flexibly, and they can even successfully accomplish previously unknown variations of tasks.