Lune

SIGGRAPH2022Top-tier venue

Learning to Get Up

Tianxin Tao, Matthew Wilson, Ruiyu Gou, Michiel van de Panne

Abstract

Getting up from an arbitrary fallen state is a basic human skill. Existing methods for learning this skill often generate highly dynamic and erratic get-up motions, which do not resemble human get-up strategies, or are based on tracking recorded human get-up motions. In this paper, we present a staged approach using reinforcement learning, without recourse to motion capture data. The method first takes advantage of a strong character model, which facilitates the discovery of solution modes. A second stage then learns to adapt the control policy to work with progressively weaker versions of the character. Finally, a third stage learns control policies that can reproduce the weaker get-up motions at much slower speeds. We show that across multiple runs, the method can discover a diverse variety of get-up strategies, and execute them at a variety of speeds. The results usually produce policies that use a final stand-up strategy that is common to the recovery motions seen from all initial states. However, we also find policies for which different strategies are seen for prone and supine initial fallen states. The learned get-up control strategies often have significant static stability, i.e., they can be paused at a variety of points during the get-up motion. We further test our method on novel constrained scenarios, such as having a leg and an arm in a cast.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

4 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Learning to Control Physically-simulated 3D Characters via Generating and Mimicking 2D Motions cites Learning Physically Simulated Tennis Skills from Broadcast Videos
  • Learning to Control Physically-simulated 3D Characters via Generating and Mimicking 2D Motions cites Perpetual Humanoid Control for Real-time Simulated Avatars
  • HuMoR: 3D Human Motion Model for Robust Pose Estimation cites Character controllers using motion VAEs
  • SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control cites Character controllers using motion VAEs
  • SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control cites HuMoR: 3D Human Motion Model for Robust Pose Estimation
  • SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control cites Robust motion in-betweening
  • Learning Physically Simulated Tennis Skills from Broadcast Videos cites Character controllers using motion VAEs
  • Perpetual Humanoid Control for Real-time Simulated Avatars cites A scalable approach to control diverse behaviors for physically simulated characters
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers4

  1. Perpetual Humanoid Control for Real-time Simulated AvatarsZhengyi Luo, Jinkun Cao, Alexander Winkler, Kris Kitani et al.ICCV 2023 · 256 citations
  2. Learning Physically Simulated Tennis Skills from Broadcast VideosHaotian Zhang, Ye Yuan, Viktor Makoviychuk, Yunrong Guo et al.SIGGRAPH 2023 · 47 citations
  3. Learning to Control Physically-simulated 3D Characters via Generating and Mimicking 2D MotionsJianan Li, Xiao Chen, Tao Huang, Tien-Tsin WongCVPR 2026 · 3 citations
  4. SMP: Reusable Score-Matching Motion Priors for Physics-Based Character ControlYuxuan Mu, Ziyu Zhang, Yi Shi, Dun Yang et al.SIGGRAPH 2026

Builds on6

  1. HuMoR: 3D Human Motion Model for Robust Pose EstimationDavis Rempe, Tolga Birdal, Aaron Hertzmann, Jimei Yang et al.ICCV 2021 · 398 citations
  2. Robust motion in-betweeningFélix G. Harvey, Mike Yurick, Derek Nowrouzezahrai, Christopher J. PalSIGGRAPH 2020 · 269 citations
  3. Character controllers using motion VAEsHung Yu Ling, Fabio Zinno, George Cheng, Michiel van de PanneSIGGRAPH 2020 · 261 citations
  4. Local motion phases for learning multi-contact character movementsSebastian Starke, Yiwei Zhao, Taku Komura, Kazi A. ZamanSIGGRAPH 2020 · 186 citations
  5. A scalable approach to control diverse behaviors for physically simulated charactersJungdam Won, Deepak Gopinath, Jessica K. HodginsSIGGRAPH 2020 · 146 citations

Related papers

  1. CoMic: Complementary Task Learning & Mimicry for Reusable SkillsLeonard Hasenclever, Fabio Pardo, Raia Hadsell, Nicolas Heess et al.ICML 2020 · 56 citations
  2. Learning to Sit: Synthesizing Human-Chair Interactions via Hierarchical ControlYu-Wei Chao, Jimei Yang, Weifeng Chen, Jia DengAAAI 2021 · 50 citations
  3. Residual Force Control for Agile Human Behavior Imitation and Extended Motion SynthesisYe Yuan, Kris KitaniNeurIPS 2020 · 105 citations
  4. Ego-Pose Estimation and Forecasting As Real-Time PD ControlYe Yuan, Kris KitaniICCV 2019 · 147 citations
  5. ASE: large-scale reusable adversarial skill embeddings for physically simulated charactersXue Bin Peng, Yunrong Guo, Lina Halper, Sergey Levine et al.SIGGRAPH 2022 · 217 citations
Dusk over the sea between two cliffs drawn in fine vertical lines