Task and motion planning methods: applications and limitations

Kai Zhang (1, 2) , Eric Lucet (2) , Julien Alexandre Dit Sandretto (1) , Selma Kchir (2) , David Filliat (1, 3)

1 U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
2 DIASI (CEA, LIST) - Département Intelligence Ambiante et Systèmes Interactifs
3 Flowers - Flowing Epigenetic Robots and Systems

Robots are required to perform more and more complicated tasks, which raises the requirement of more intelligent planning algorithms. As a domain having been explored for decades, task and motion planning (TAMP) methods have achieved significant results, but several challenges remain to be solved. This paper summarizes the development of TAMP from solving objectives, simulation environments, methods and remaining limitations. In particular, it compares different simulation environments and methods used in different tasks aiming to provide a practical guide and overview for the beginners.

Mots clés: Task and motion planning; simulation environment; learning methods

Domaines: Robotique [cs.RO]

Kai Zhang, Eric Lucet, Julien Alexandre Dit Sandretto, Selma Kchir, David Filliat. Task and motion planning methods: applications and limitations. ICINCO 2022 - 19th International Conference on Informatics in Control, Automation and Robotics, Jul 2022, Lisbonne, Portugal. pp.476-483, ⟨10.5220/0011314000003271⟩. ⟨hal-03744923⟩