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

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › 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.

Originalsprog	Engelsk
Titel	Advances in Computational Intelligence : 15th International Work-Conference on Artificial Neural Networks, IWANN 2019, Gran Canaria, Spain, June 12-14, 2019, Proceedings, Part II
Redaktører	Ignacio Rojas, Gonzalo Joya, Andreu Catala
Antal sider	12
Forlag	Springer
Publikationsdato	jun. 2019
Sider	869-880
ISBN (Trykt)	978-3-030-20517-1
ISBN (Elektronisk)	978-3-030-20518-8
DOI	https://doi.org/10.1007/978-3-030-20518-8_72
Status	Udgivet - jun. 2019
Begivenhed	International Work-Conference on Artificial Neural Networks - , Spanien Varighed: 12 jun. 2019 → 14 jun. 2019 Konferencens nummer: 15

Konference

Konference	International Work-Conference on Artificial Neural Networks
Nummer	15
Land/Område	Spanien
Periode	12/06/2019 → 14/06/2019

Navn	Lecture Notes in Computer Science
Vol/bind	11507
ISSN	0302-9743

Adgang til dokumentet

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

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

Andre filer og links

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

Citationsformater

Carlsen, C. S., & Palamas, G. (2019). Evolving Balancing Controllers for Biped Characters in Games. I I. Rojas, G. Joya, & A. Catala (red.), Advances in Computational Intelligence : 15th International Work-Conference on Artificial Neural Networks, IWANN 2019, Gran Canaria, Spain, June 12-14, 2019, Proceedings, Part II (s. 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. red. / Ignacio Rojas ; Gonzalo Joya ; Andreu Catala. Springer, 2019. s. 869-880 (Lecture Notes in Computer Science, Bind 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. i I Rojas, G Joya & A Catala (red), 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, bind 11507, s. 869-880, International Work-Conference on Artificial Neural Networks, Spanien, 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. red. / Ignacio Rojas; Gonzalo Joya; Andreu Catala. Springer, 2019. s. 869-880 (Lecture Notes in Computer Science, Bind 11507).

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › 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. I Rojas I, Joya G, Catala A, red., 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. s. 869-880. (Lecture Notes in Computer Science, Bind 11507). doi: 10.1007/978-3-030-20518-8_72

Evolving Balancing Controllers for Biped Characters in Games

Abstract

Konference

Adgang til dokumentet

AUB Link

Andre filer og links

Fingeraftryk

Citationsformater