Metraipolis › archive › dc_fe96efa53e86

CuPIQP: A Batched and Differentiable QP Solver on GPUs for Robot Learning and Control — arXiv:2610.41021

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41021
License (as archived)
CC0-1.0
Archived
2026-11-02T04:57:17.596Z
SHA-256 of the archived text
3e3d0cb69bbc7f964e2928d975d4080fc708e7196174fcc2ff741603f6f52c0e
Stable URL of this page
https://metraipolis.com/documento/dc_fe96efa53e86

How to cite

CuPIQP: A Batched and Differentiable QP Solver on GPUs for Robot Learning and Control — arXiv:2610.41021 — arXiv (en), https://arxiv.org/abs/2610.41021 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fe96efa53e86 (Metraipolis archive dc_fe96efa53e86, sha256 3e3d0cb69bbc7f964e2928d975d4080fc708e7196174fcc2ff741603f6f52c0e)
BibTeX
@misc{dcfe96efa53e86,
  title = {CuPIQP: A Batched and Differentiable QP Solver on GPUs for Robot Learning and Control — arXiv:2610.41021},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41021},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fe96efa53e86; sha256 3e3d0cb69bbc7f964e2928d975d4080fc708e7196174fcc2ff741603f6f52c0e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41021. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Quadratic programs (QPs) are fundamental building blocks of many robotic tasks such as inverse kinematics, whole-body control, and model predictive control. Extending these methods to large-scale robot learning and control requires solving many QPs concurrently and, for end-to-end learning, differentiating through their solutions. Efficient batched optimization is therefore essential to bringing established model-based methods into GPU-based robotics pipelines. We present \textsc{cuPIQP}, a batched and differentiable QP solver on GPUs based on a proximal interior-point method, with unified support for dense, sparse, and multistage problems. The solver exploits parallelism across independent QPs and their internal structure while preserving per-problem numerical updates and termination decisions. Benchmarks with up to 16384 QPs per batch demonstrate solve-time speedups of up to $18.8\times$ over \textsc{Moreau} and $4.26\times$ over eight-core \textsc{PIQP}. In an end-to-end learning task, \textsc{cuPIQP} accelerates training by $4.6\times$ over \textsc{QPAX} and $7.8\times$ over \textsc{Moreau}. By reducing the computational cost, \textsc{cuPIQP} provides efficient, reusable infrastructure for integrating model-based optimization into large-scale robot learning and control.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.OC, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.41021 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-02T04:46:57.644Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).