Key points
- DOC establishes differentiable optimal control for retargeting captured or authored motion onto legged robots.
- It received a SIGGRAPH 2023 Best Paper award (Disney Research and ETH Zurich).
- It bridges digital animation authoring and physical robotic character performance.
Summary
DOC, by Grandia, Farshidian, Knoop, Schumacher, Hutter and Bacher from Disney Research and ETH Zurich, presents a differentiable optimal control framework for retargeting authored or motion-captured animation onto physically simulated legged robots. The work received a Best Paper award at SIGGRAPH 2023. Its primary nexus is robotic-character performance, with animation-education relevance as the bridge between digital animation authoring and the physical execution of character motion -- a connection of increasing practical importance as animatronic and robotic characters enter theme-park and performance contexts.
Related items
- DeepPhase: Periodic Autoencoders for Learning Motion Phase Manifolds
- A deep learning framework for character motion synthesis and editing (SIGGRAPH 2016 / SIGGRAPH 2026 Test-of-Time award)
Source
Source: ACM Transactions on Graphics (SIGGRAPH 2023) ↗ (Research)
Cite this item
Grandia, R., Farshidian, F., Knoop, E., Schumacher, C., Hutter, M. & Bacher, M. (2023). ‘DOC: Differentiable Optimal Control for Retargeting Motions onto Legged Robots’, ACM Transactions on Graphics (SIGGRAPH 2023). Available at: https://dl.acm.org/doi/10.1145/3592454
Your reference manager can also read this page directly: with the Zotero (or Mendeley) browser connector installed, save it straight to your library. Whole-collection exports: RIS, BibTeX, CSL-JSON.