arXiv Open Access 2025

Beyond Task and Motion Planning: Hierarchical Robot Planning with General-Purpose Skills

Benned Hedegaard Yichen Wei Ahmed Jaafar Stefanie Tellex George Konidaris +1 lainnya
Lihat Sumber

Abstrak

Task and motion planning is a well-established approach for solving long-horizon robot planning problems. However, traditional methods assume that each task-level robot action, or skill, can be reduced to kinematic motion planning. We address the challenge of combining motion planning with closed-loop motor controllers that go beyond mere kinematic considerations. We propose a novel framework that integrates these policies into motion planning using Composable Interaction Primitives (CIPs), enabling the use of diverse, non-composable pre-learned skills in hierarchical robot planning. We validate our Task and Skill Planning (TASP) approach through real-world experiments on a bimanual manipulator and a mobile manipulator, demonstrating that CIPs allow diverse robots to combine motion planning with general-purpose skills to solve complex, long-horizon tasks.

Topik & Kata Kunci

Penulis (6)

B

Benned Hedegaard

Y

Yichen Wei

A

Ahmed Jaafar

S

Stefanie Tellex

G

George Konidaris

N

Naman Shah

Format Sitasi

Hedegaard, B., Wei, Y., Jaafar, A., Tellex, S., Konidaris, G., Shah, N. (2025). Beyond Task and Motion Planning: Hierarchical Robot Planning with General-Purpose Skills. https://arxiv.org/abs/2504.17901

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓