Author:
Pek Christian,Schuppe Georg Friedrich,Esposito Francesco,Tumova Jana,Kragic Danica
Abstract
AbstractMany tasks require robots to manipulate objects while satisfying a complex interplay of spatial and temporal constraints. For instance, a table setting robot first needs to place a mug and then fill it with coffee, while satisfying spatial relations such as forks need to placed left of plates. We propose the spatio-temporal framework SpaTiaL that unifies the specification, monitoring, and planning of object-oriented robotic tasks in a robot-agnostic fashion. SpaTiaL is able to specify diverse spatial relations between objects and temporal task patterns. Our experiments with recorded data, simulations, and real robots demonstrate how SpaTiaL provides real-time monitoring and facilitates online planning. SpaTiaL is open source and easily expandable to new object relations and robotic applications.
Funder
Wallenberg AI, Autonomous Systems and Software Program
Swedish Research Council
Knut and Alice Wallenberg Foundation
Publisher
Springer Science and Business Media LLC
Reference110 articles.
1. Agostini, A., & Lee, D. (2020). Efficient state abstraction using object-centered predicates for manipulation planning. Preprint retrieved from preprint arXiv:2007.08251
2. Aineto, D., Jiménez, S., & Onaindia, E. (2018). Learning STRIPS action models with classical planning. In Proceeding of the international conference on automated planning and scheduling.
3. Allen, J. F. (1983). Maintaining knowledge about temporal intervals. Communications of the ACM, 26(11), 832–843.
4. Alur, R., Feder, T., & Henzinger, T. A. (1996). The benefits of relaxing punctuality. Journal of the ACM, 43(1), 116–146.
5. Baier, C., & Katoen, J. P. (2008). Principles of model checking. MIT Press.