Expanding the capabilities of robots to achieve complex objectives in new environments requires novel reasoning systems. Everyday tasks in the physical world, such as the table setting in Fig. 1, couple discrete decisions about objects and actions with geometric decisions about collision free motion. Robotics has traditionally treated these issues—task planning and motion planning—in isolation, thus missing their potential interactions. Instead, the joint approach of Task–Motion Planning (TMP) addresses this inherent coupling. Moreover, reasoning in concert about overall objectives and concrete motions enables the high-level specification of behavior, mitigating typically intensive system integration efforts required in robotics. We address the need for underlying models and principles in integrated robot manipulation with a new planning and execution framework that is adaptable to new robots, domains, and algorithms.