Browsing by Author "Dantam, Neil T."
Now showing 1 - 3 of 3
Results Per Page
Sort Options
Item An incremental constraint-based framework for task and motion planning(Sage, 2018) Dantam, Neil T.; Kingston, Zachary K.; Chaudhuri, Swarat; Kavraki, Lydia E.We present a new constraint-based framework for task and motion planning (TMP). Our approach is extensible, probabilistically complete, and offers improved performance and generality compared with a similar, state-of-the-art planner. The key idea is to leverage incremental constraint solving to efficiently incorporate geometric information at the task level. Using motion feasibility information to guide task planning improves scalability of the overall planner. Our key abstractions address the requirements of manipulation and object rearrangement. We validate our approach on a physical manipulator and evaluate scalability on scenarios with many objects and long plans, showing order-of-magnitude gains compared with the benchmark planner and improved scalability from additional geometric guidance. Finally, in addition to describing a new method for TMP and its implementation on a physical robot, we also put forward requirements and abstractions for the development of similar planners in the future.Item Platform-Independent Benchmarks for Task and Motion Planning(IEEE, 2018) Lagriffoul, Fabien; Dantam, Neil T.; Garrett, Caelan; Akbari, Aliakbar; Srivastava, Siddharth; Kavraki, Lydia E.We present the first platform-independent evaluation method for task and motion planning (TAMP). Previously point, various problems have been used to test individual planners for specific aspects of TAMP. However, no common set of metrics, formats, and problems have been accepted by the community. We propose a set of benchmark problems covering the challenging aspects of TAMP and a planner-independent specification format for these problems. Our objective is to better evaluate and compare TAMP planners, foster communication, and progress within the field, and lay a foundation to better understand this class of planning problems.Item The Task Motion Kit(2016-10-31) Chaudhuri, Swarat; Dantam, Neil T.; Kavraki, Lydia E.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.