Closing the Motion Execution Gap: From Semantic Motion Task Constraints to Kinematic Control
Simon Stelter, Vanessa Hassouna, Malte Huerkamp, Michael Beetz
TLDR
This paper closes the Motion Execution Gap, translating high-level semantic task constraints into executable robot motions via Motion Statecharts.
Key contributions
- Introduces Motion Statecharts for executable symbolic representation of complex, constrained robot motions.
- Uses a unified differentiable kinematic world model for world-centric motion specification and generalization.
- Employs an lMPC-based task-function approach with jerk bounds for smooth motion execution and task switches.
- Demonstrates cross-platform transferability on eight diverse robot platforms, open-sourced as Giskard.
Why it matters
This paper provides a robust framework, Giskard, for bridging the gap between abstract task descriptions and concrete robot actions. Its ability to generalize across various robots and environments significantly advances practical robot autonomy, making complex motion planning more accessible and reliable.
Original Abstract
This paper addresses the Motion Execution Gap, the disconnect between high-level symbolic task descriptions using semantic constraints and executable robot motions. Motion Statecharts are introduced as an executable symbolic representation for complex motions. They allow the arbitrary arrangement of motion constraints, monitors or nested statecharts in parallel and sequence. World-centric motion specification and generalization across embodiments are enabled through the use of a unified differentiable kinematic world model of both, robots and environments. Motion execution is realized through a lMPC-based implementation of the task-function approach, in which smooth transitions during task switches are ensured using jerk bounds. Cross-platform transferability was demonstrated by deploying the method on eight robot platforms, operating in diverse environments. The proposed framework is called Giskard and is available open source: https://github.com/cram2/cognitive_robot_abstract_machine.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.