N. T. Dantam, S. Chaudhuri, and L. E. Kavraki, “The Task Motion Kit,” Robotics and Automation Magazine, vol. 25, no. 3, pp. 61–70, Sep. 2018.
Robots require novel reasoning systems to achieve complex objectives in new environments. Daily activities in the physical world combine two types of reasoning: discrete and continuous. For example, to set the table, the robot must make discrete decisions about which and in what order to pick objects, and it must execute these decisions by computing continuous motions to reach objects or desired locations. Robotics has traditionally treated these issues in isolation. Reasoning about discrete events is referred to as task planning, while reasoning about and computing continuous motions is in the realm of motion planning. However, several recent works have shown that separating task planning from motion planning is problematic. This article provides an introduction to task-motion planning (TMP), this concept tightly couples task planning and motion planning, producing a sequence of steps that can actually be executed by a real robot. The implementation and use of an open-source TMP framework tht is adaptable to new robots is also discussed.
Publisher: http://dx.doi.org/10.1109/MRA.2018.2815081
PDF preprint: http://kavrakilab.org/publications/dantam2018task-motion-kit.pdf