Skip to main content

Research · Technical

DOC: Differentiable Optimal Control for Retargeting Motions onto Legged Robots

ACM Transactions on Graphics (SIGGRAPH 2023) · Grandia, R., Farshidian, F., Knoop, E., Schumacher, C., Hutter, M., Bacher, M. · Jul 2023

Key points

  1. DOC establishes differentiable optimal control for retargeting captured or authored motion onto legged robots.
  2. It received a SIGGRAPH 2023 Best Paper award (Disney Research and ETH Zurich).
  3. 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.

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.