{"type":"ScholarlyArticle","title":"Closing the Motion Execution Gap: From Semantic Motion Task Constraints to Kinematic Control","authors":[{"name":"Simon Stelter","slug":"simon-stelter","given":"Simon","family":"Stelter","affiliation":""},{"name":"Vanessa Hassouna","slug":"vanessa-hassouna","given":"Vanessa","family":"Hassouna","affiliation":""},{"name":"Malte Huerkamp","slug":"malte-huerkamp","given":"Malte","family":"Huerkamp","affiliation":""},{"name":"Michael Beetz","slug":"michael-beetz","given":"Michael","family":"Beetz","affiliation":""}],"abstract":"This paper addresses the Motion Execution Gap, the disconnect between high-level symbolic task descriptions using semantic constraints and executable robot motions.\r\n\\textbf{Motion Statecharts} are introduced as an executable symbolic representation for complex motions.\r\nThey allow the arbitrary arrangement of motion constraints, monitors or nested statecharts in parallel and sequence.\r\nWorld-centric motion specification and generalization across embodiments are enabled through the use of a unified differentiable kinematic world model of both, robots and environments.\r\nMotion execution is realized through a \\ac{lmpc}-based implementation of the task-function approach, in which smooth transitions during task switches are ensured using jerk bounds.\r\nCross-platform transferability was demonstrated by deploying the method on eight robot platforms, operating in diverse environments.\r\nThe proposed framework is called Giskard and is available open source (https://github.com/cram2/cognitive_robot_abstract_machine).","doi":"10.24963/ijcai.2026/845","url":"https://ijcai.org/proceedings/2026/845","pdf":"https://ijcai.org/proceedings/2026/0845.pdf","markdown":"https://ijcai.org/proceedings/2026/845.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/845","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"AI and Robotics","track":"AI and Robotics","number":845,"pages":{"first":7601,"last":7609},"keywords":["Structured, semantic, and explicit world models, digital twins, and action representations: Explicit action representations such as task schemas, scripts, and parameterized skills","Robot control, planning, and execution with guarantees: Online monitoring, explanation, and adaptation","Structured, semantic, and explicit world models, digital twins, and action representations: Structured world models and semantic digital twins","Robot control, planning, and execution with guarantees: Architectures connecting high-level intent and constraints to low-level trajectories"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}