Learning to Brachiate via Simplified Model Imitation

In Proceedings of SIGGRAPH 2022

DANIELE REDA*, University of British Columbia, Canada HUNG YU LING*, University of British Columbia, Canada MICHIEL VAN DE PANNE, University of British Columbia, Canada * indicates equal contribution.


Paper: ArXiv / Code: GitHub

Brachiation is the primary form of locomotion for gibbons and siamangs, in which these primates swing from tree limb to tree limb using only their arms. It is challenging to control because of the limited control authority, the required advance planning, and the precision of the required grasps. We present a novel approach to this problem using reinforcement learning, and as demonstrated on a finger-less 14-link planar model that learns to brachiate across challenging handhold sequences. Key to our method is the use of a simplified model, a point mass with a virtual arm, for which we first learn a policy that can brachiate across handhold sequences with a prescribed order. This facilitates the learning of the policy for the full model, for which it provides guidance by providing an overall center-of-mass trajectory to imitate, as well as for the timing of the holds. Lastly, the simplified model can also readily be used for planning suitable sequences of handholds in a given environment. Our results demonstrate brachiation motions with a variety of durations for the flight and hold phases, as well as emergent extra back-and-forth swings when this proves useful. The system is evaluated with a variety of ablations. The method enables future work towards more general 3D brachiation, as well as using simplified model imitation in other settings.


In our two-stage imitation learning system, the simplified model allows for efficient exploration of the solution space and produces physically-feasible reference trajectories for the full model to imitate.

Illustration of our two-stage simplified model imitation learning system


Gibbon Conservation

Gibbons are among the most vulnerable and endangered species alive. Gibbons are at risk due to the destruction of their habitat and illegal wildlife pet trade. Please consider donating to Gibbon Rehabilitation Project to protect gibbons and their habitat.


  author = {Reda, Daniele and Ling, Hung Yu and van de Panne, Michiel},
  title = {Learning to Brachiate via Simplified Model Imitation},
  year = {2022},
  publisher = {Association for Computing Machinery},
  booktitle = {ACM SIGGRAPH 2022 Conference Proceedings},
  articleno = {24},
  numpages = {9},
  series = {SIGGRAPH '22}

Web Demo

This demo is built using PixiJS. The motions are pre-recorded kinematic trajectories; please refer to the code for pretrained controllers and physics environments. See paper for more details.