Discovering Diverse Athletic Jumping Strategies

by   Zhiqi Yin, et al.

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.



page 10

page 11

page 12

page 13

page 14


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

A longstanding goal in character animation is to combine data-driven spe...

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

Synthesizing graceful and life-like behaviors for physically simulated c...

Realistic Physics Based Character Controller

Over the course of the last several years there was a strong interest in...

TEMOS: Generating diverse human motions from textual descriptions

We address the problem of generating diverse 3D human motions from textu...

Probabilistic Character Motion Synthesis using a Hierarchical Deep Latent Variable Model

We present a probabilistic framework to generate character animations ba...

Learning to Use Chopsticks in Diverse Styles

Learning dexterous manipulation skills is a long-standing challenge in c...

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.