A Steering Algorithm for Redirected Walking Using Reinforcement Learning

Redirected Walking (RDW) steering algorithms have traditionally relied on human-engineered logic. However, recent advances in reinforcement learning (RL) have produced systems that surpass human performance on a variety of control tasks. This paper investigates the potential of using RL to develop a...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on visualization and computer graphics Vol. 26; no. 5; pp. 1955 - 1963
Main Authors: Strauss, Ryan R., Ramanujan, Raghuram, Becker, Andrew, Peck, Tabitha C.
Format: Journal Article
Language:English
Published: United States IEEE 01.05.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithms
Artificial neural networks
Computer Graphics
Computer simulation
Control tasks
Deep Learning
Heuristic algorithms
Human performance
Humans
Learning (artificial intelligence)
Legged locomotion
Locomotion
Machine learning
Meters
Prediction algorithms
Redirected Walking
Reinforcement Learning
Space exploration
Steering
Steering Algorithms
Tracking
Video Games
Virtual environments
Virtual Reality
Walking
Walking - physiology
ISSN:1077-2626, 1941-0506, 1941-0506
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Redirected Walking (RDW) steering algorithms have traditionally relied on human-engineered logic. However, recent advances in reinforcement learning (RL) have produced systems that surpass human performance on a variety of control tasks. This paper investigates the potential of using RL to develop a novel reactive steering algorithm for RDW. Our approach uses RL to train a deep neural network that directly prescribes the rotation, translation, and curvature gains to transform a virtual environment given a user's position and orientation in the tracked space. We compare our learned algorithm to steer-to-center using simulated and real paths. We found that our algorithm outperforms steer-to-center on simulated paths, and found no significant difference on distance traveled on real paths. We demonstrate that when modeled as a continuous control problem, RDW is a suitable domain for RL, and moving forward, our general framework provides a promising path towards an optimal RDW steering algorithm.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1077-2626
1941-0506
1941-0506
DOI:10.1109/TVCG.2020.2973060