Few things in space flight are routine. Before each time MDA operates the International Space Station’s famous Canadarm2, thousands of simulations must be performed to ensure the success and safety of the operation. This research intends to streamline the process of operations planning for Canadarm2 by using machine learning to predict key outputs from these simulations. If a particular case appears problematic, the algorithm can suggest why and allow MDA to focus their efforts on preventing the issue without having to perform a lengthy analysis of all possible cases. This approach to mission planning can also provide a tool to advise operators in real time of the estimated probability of success. Future applications may extend beyond Canadarm2 to include planetary rovers or even robot-assisted surgery.