Discovering Diverse Athletic Jumping Strategies

05/02/2021
by   Zhiqi Yin, et al.
3

We present a framework that enables the discovery of diverse and natural-looking motion strategies for athletic skills such as the high jump. The strategies are realized as control policies for physics-based characters. Given a task objective and an initial character configuration, the combination of physics simulation and deep reinforcement learning (DRL) provides a suitable starting point for automatic control policy training. To facilitate the learning of realistic human motions, we propose a Pose Variational Autoencoder (P-VAE) to constrain the actions to a subspace of natural poses. In contrast to motion imitation methods, a rich variety of novel strategies can naturally emerge by exploring initial character states through a sample-efficient Bayesian diversity search (BDS) algorithm. A second stage of optimization that encourages novel policies can further enrich the unique strategies discovered. Our method allows for the discovery of diverse and novel strategies for athletic jumping motions such as high jumps and obstacle jumps with no motion examples and less reward engineering than prior work.

READ FULL TEXT

Authors

page 10

page 11

page 12

page 13

page 14

04/08/2018

DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills

A longstanding goal in character animation is to combine data-driven spe...
04/05/2021

AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control

Synthesizing graceful and life-like behaviors for physically simulated c...
06/12/2020

Realistic Physics Based Character Controller

Over the course of the last several years there was a strong interest in...
04/25/2022

TEMOS: Generating diverse human motions from textual descriptions

We address the problem of generating diverse 3D human motions from textu...
10/20/2020

Probabilistic Character Motion Synthesis using a Hierarchical Deep Latent Variable Model

We present a probabilistic framework to generate character animations ba...
05/28/2022

Learning to Use Chopsticks in Diverse Styles

Learning dexterous manipulation skills is a long-standing challenge in c...
08/20/2019

Learning to Sit: Synthesizing Human-Chair Interactions via Hierarchical Control

Recent progress on physics-based character animation has shown impressiv...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.