Traditionally, robots are limited to controlled environments such as caged areas in factories. When robots move to uncontrolled environments where humans are present, the robot must consider the possible behaviors of the humans. To ensure the robot completes its task, a class of approaches called reactive synthesis has been employed to construct reactive strategies for robots. The reactive strategy chooses robot actions based on the observed human behaviors, and guarantees task completion. This thesis expands the capabilities of reactive synthesis to finite-horizon tasks with resource cost constraints to manipulation domains, and to more complex problems. The algorithms in this thesis are demonstrated on a UR5 robot performing pick-and-place tasks. Existing works in robotic reactive synthesis focused on infinite-horizon tasks (e.g. surveillance) because they rely on existing reactive synthesis tools from the program synthesis community. However, many robotic tasks, such as assembly and delivery, are finite-horizon. This thesis presents a reactive synthesis framework for finite-horizon tasks. By focusing on finite-horizon domains, we not only guarantee task completion, but also minimize the robot’s resource consumption during execution. Reactive synthesis can only be directly performed on finite structures, but robotic domains are continuous and infinite. Thus an abstraction that discretizes the domain is required. Existing works in reactive synthesis have focused on navigation problems, where abstraction is achieved using workspace decomposition. This thesis presents an appropriate abstraction for manipulation domains. This abstraction allows reactive synthesis to be applied to manipulation domains. This thesis also presents an algorithm to make reactive synthesis more scalable. Previous synthesis algorithms in robotics used either explicit state or formulaic representations. Such representations fail to utilize the structure of robotic problems. This thesis presents a synthesis algorithm that represents the domains symbolically using binary decision diagrams, which are more compact and take advantage of the structure in robotic problems. Order-of-magnitude speed-ups over existing approaches are observed on robotics-related benchmarks. This speed-up allows reactive synthesis to be performed on much larger domains.