Evolving Balancing Controllers for Biped Characters in Games

Christopher Schinkel Carlsen; George Palamas

doi:10.1007/978-3-030-20518-8_72

Evolving Balancing Controllers for Biped Characters in Games

Christopher Schinkel Carlsen, George Palamas

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

Abstract

This paper compares two approaches to physics based, balancing systems, for 3D biped characters that can react to dynamic environments. The first approach, based on the concept of proprioception, use a neuro-controller to define the position and orientation of the joints involved in the motion. The second approach
use a self-adaptive Proportional Derivative (PD) controller along with a neural network. Both neural networks were trained using a Genetic Algorithm (GA). The study showed that both approaches were capable of achieving balance and the GA proved to work well as a search strategy for both the neuro-controller and the PD-controller. The results also showed that the neuro-controller performed better but the PD-controller was more flexible and capable to recover under external disturbances such as wind drag and momentary collisions with objects.

Original language	English
Title of host publication	Advances in Computational Intelligence : 15th International Work-Conference on Artificial Neural Networks, IWANN 2019, Gran Canaria, Spain, June 12-14, 2019, Proceedings, Part II
Editors	Ignacio Rojas, Gonzalo Joya, Andreu Catala
Number of pages	12
Publisher	Springer
Publication date	Jun 2019
Pages	869-880
ISBN (Print)	978-3-030-20517-1
ISBN (Electronic)	978-3-030-20518-8
DOIs	https://doi.org/10.1007/978-3-030-20518-8_72
Publication status	Published - Jun 2019
Event	International Work-Conference on Artificial Neural Networks - , Spain Duration: 12 Jun 2019 → 14 Jun 2019 Conference number: 15

Conference

Conference	International Work-Conference on Artificial Neural Networks
Number	15
Country/Territory	Spain
Period	12/06/2019 → 14/06/2019

Series	Lecture Notes in Computer Science
Volume	11507
ISSN	0302-9743

Keywords

Evolutionary
Neural-network
Neuro-controller
Procedural animation
Virtual-agent

Access to Document

10.1007/978-3-030-20518-8_72

AUB Link

Search for the material in Aalborg University Library's search engine

Cite this

Carlsen, C. S., & Palamas, G. (2019). Evolving Balancing Controllers for Biped Characters in Games. In I. Rojas, G. Joya, & A. Catala (Eds.), Advances in Computational Intelligence : 15th International Work-Conference on Artificial Neural Networks, IWANN 2019, Gran Canaria, Spain, June 12-14, 2019, Proceedings, Part II (pp. 869-880). Springer. https://doi.org/10.1007/978-3-030-20518-8_72

Carlsen, Christopher Schinkel ; Palamas, George. / Evolving Balancing Controllers for Biped Characters in Games. Advances in Computational Intelligence : 15th International Work-Conference on Artificial Neural Networks, IWANN 2019, Gran Canaria, Spain, June 12-14, 2019, Proceedings, Part II. editor / Ignacio Rojas ; Gonzalo Joya ; Andreu Catala. Springer, 2019. pp. 869-880 (Lecture Notes in Computer Science, Vol. 11507).

@inproceedings{70d751f03a884efdbe6401894c595372,

title = "Evolving Balancing Controllers for Biped Characters in Games",

abstract = "This paper compares two approaches to physics based, balancing systems, for 3D biped characters that can react to dynamic environments. The first approach, based on the concept of proprioception, use a neuro-controller to define the position and orientation of the joints involved in the motion. The second approachuse a self-adaptive Proportional Derivative (PD) controller along with a neural network. Both neural networks were trained using a Genetic Algorithm (GA). The study showed that both approaches were capable of achieving balance and the GA proved to work well as a search strategy for both the neuro-controller and the PD-controller. The results also showed that the neuro-controller performed better but the PD-controller was more flexible and capable to recover under external disturbances such as wind drag and momentary collisions with objects.",

keywords = "Evolutionary, Neural-network, Neuro-controller, Procedural animation, Virtual-agent",

author = "Carlsen, {Christopher Schinkel} and George Palamas",

year = "2019",

month = jun,

doi = "10.1007/978-3-030-20518-8_72",

language = "English",

isbn = "978-3-030-20517-1",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "869--880",

editor = "Ignacio Rojas and Gonzalo Joya and Andreu Catala",

booktitle = "Advances in Computational Intelligence",

address = "Germany",

note = "International Work-Conference on Artificial Neural Networks, IWANN ; Conference date: 12-06-2019 Through 14-06-2019",

}

Carlsen, CS & Palamas, G 2019, Evolving Balancing Controllers for Biped Characters in Games. in I Rojas, G Joya & A Catala (eds), Advances in Computational Intelligence : 15th International Work-Conference on Artificial Neural Networks, IWANN 2019, Gran Canaria, Spain, June 12-14, 2019, Proceedings, Part II. Springer, Lecture Notes in Computer Science, vol. 11507, pp. 869-880, International Work-Conference on Artificial Neural Networks, Spain, 12/06/2019. https://doi.org/10.1007/978-3-030-20518-8_72

Evolving Balancing Controllers for Biped Characters in Games. / Carlsen, Christopher Schinkel; Palamas, George.
Advances in Computational Intelligence : 15th International Work-Conference on Artificial Neural Networks, IWANN 2019, Gran Canaria, Spain, June 12-14, 2019, Proceedings, Part II. ed. / Ignacio Rojas; Gonzalo Joya; Andreu Catala. Springer, 2019. p. 869-880 (Lecture Notes in Computer Science, Vol. 11507).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - Evolving Balancing Controllers for Biped Characters in Games

AU - Carlsen, Christopher Schinkel

AU - Palamas, George

N1 - Conference code: 15

PY - 2019/6

Y1 - 2019/6

N2 - This paper compares two approaches to physics based, balancing systems, for 3D biped characters that can react to dynamic environments. The first approach, based on the concept of proprioception, use a neuro-controller to define the position and orientation of the joints involved in the motion. The second approachuse a self-adaptive Proportional Derivative (PD) controller along with a neural network. Both neural networks were trained using a Genetic Algorithm (GA). The study showed that both approaches were capable of achieving balance and the GA proved to work well as a search strategy for both the neuro-controller and the PD-controller. The results also showed that the neuro-controller performed better but the PD-controller was more flexible and capable to recover under external disturbances such as wind drag and momentary collisions with objects.

AB - This paper compares two approaches to physics based, balancing systems, for 3D biped characters that can react to dynamic environments. The first approach, based on the concept of proprioception, use a neuro-controller to define the position and orientation of the joints involved in the motion. The second approachuse a self-adaptive Proportional Derivative (PD) controller along with a neural network. Both neural networks were trained using a Genetic Algorithm (GA). The study showed that both approaches were capable of achieving balance and the GA proved to work well as a search strategy for both the neuro-controller and the PD-controller. The results also showed that the neuro-controller performed better but the PD-controller was more flexible and capable to recover under external disturbances such as wind drag and momentary collisions with objects.

KW - Evolutionary

KW - Neural-network

KW - Neuro-controller

KW - Procedural animation

KW - Virtual-agent

UR - http://www.scopus.com/inward/record.url?scp=85067552526&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-20518-8_72

DO - 10.1007/978-3-030-20518-8_72

M3 - Article in proceeding

SN - 978-3-030-20517-1

T3 - Lecture Notes in Computer Science

SP - 869

EP - 880

BT - Advances in Computational Intelligence

A2 - Rojas, Ignacio

A2 - Joya, Gonzalo

A2 - Catala, Andreu

PB - Springer

T2 - International Work-Conference on Artificial Neural Networks

Y2 - 12 June 2019 through 14 June 2019

ER -

Carlsen CS, Palamas G. Evolving Balancing Controllers for Biped Characters in Games. In Rojas I, Joya G, Catala A, editors, Advances in Computational Intelligence : 15th International Work-Conference on Artificial Neural Networks, IWANN 2019, Gran Canaria, Spain, June 12-14, 2019, Proceedings, Part II. Springer. 2019. p. 869-880. (Lecture Notes in Computer Science, Vol. 11507). doi: 10.1007/978-3-030-20518-8_72

Evolving Balancing Controllers for Biped Characters in Games

Abstract

Conference

Keywords

Access to Document

AUB Link

Other files and links

Fingerprint

Cite this