Frezzato, AnthonyTangri, ArshAndrews, SheldonDominik L. MichelsSoeren Pirk2022-08-102022-08-1020221467-8659https://doi.org/10.1111/cgf.14636https://diglib.eg.org:443/handle/10.1111/cgf14636We propose a method for synthesizing get-up motions for physics-based humanoid characters. Beginning from a supine or prone state, our objective is not to imitate individual motion clips, but to produce motions that match input curves describing the style of get-up motion. Our framework uses deep reinforcement learning to learn control policies for the physics-based character. A latent embedding of natural human poses is computed from a motion capture database, and the embedding is furthermore conditioned on the input features. We demonstrate that our approach can synthesize motions that follow the style of user authored curves, as well as curves extracted from reference motions. In the latter case, motions of the physics-based character resemble the original motion clips. New motions can be synthesized easily by changing only a small number of controllable parameters. We also demonstrate the success of our controllers on rough and inclined terrain.CCS Concepts: Computing methodologies --> Physical simulation; Theory of computation --> Reinforcement learningComputing methodologiesPhysical simulationTheory of computationReinforcement learning10.1111/cgf.14636207-21812 pages