Emergence of adaptive behaviors by redundant robots - Robustness to changes environment and failures

K. Ito; A. Gofuku

doi:10.1109/CEC.2003.1299412

Emergence of adaptive behaviors by redundant robots - Robustness to changes environment and failures

K. Ito, A. Gofuku

Research output: Contribution to conference › Paper › peer-review

4 Citations (Scopus)

Abstract

Acquiring adaptive behaviors of robots automatically is one of the most interesting topics of the evolutionary systems. In previous works, we have developed an adaptive autonomous control method for redundant robots. The QDSEGA is one of the methods that we have proposed for them. The QDSEGA is realized by combining Q-learning and GA, and it can acquire suitable behaviors by adapting a movement of a robot for a task. In this paper, we focus on the adaptability of the QDSEGA and discuss the robustness of the autonomous redundant robot that is controlled by the QDSEGA. To demonstrate the effectiveness of the QDSEGA, simulations of obstacle avoidance by a 10-link manipulator in the changeable environment and locomotion by a 12-legged robot with failures have been carried out, and as a result, adaptive behaviors for each environment and each broken body have emerged.

Original language	English
Pages	2572-2579
Number of pages	8
DOIs	https://doi.org/10.1109/CEC.2003.1299412
Publication status	Published - 2003
Event	2003 Congress on Evolutionary Computation, CEC 2003 - Canberra, ACT, Australia Duration: Dec 8 2003 → Dec 12 2003

Other

Other	2003 Congress on Evolutionary Computation, CEC 2003
Country/Territory	Australia
City	Canberra, ACT
Period	12/8/03 → 12/12/03

ASJC Scopus subject areas

Computational Mathematics

Access to Document

10.1109/CEC.2003.1299412

Cite this

@conference{d8de84b7602d4cf3b6157e3bc2583142,

title = "Emergence of adaptive behaviors by redundant robots - Robustness to changes environment and failures",

abstract = "Acquiring adaptive behaviors of robots automatically is one of the most interesting topics of the evolutionary systems. In previous works, we have developed an adaptive autonomous control method for redundant robots. The QDSEGA is one of the methods that we have proposed for them. The QDSEGA is realized by combining Q-learning and GA, and it can acquire suitable behaviors by adapting a movement of a robot for a task. In this paper, we focus on the adaptability of the QDSEGA and discuss the robustness of the autonomous redundant robot that is controlled by the QDSEGA. To demonstrate the effectiveness of the QDSEGA, simulations of obstacle avoidance by a 10-link manipulator in the changeable environment and locomotion by a 12-legged robot with failures have been carried out, and as a result, adaptive behaviors for each environment and each broken body have emerged.",

author = "K. Ito and A. Gofuku",

year = "2003",

doi = "10.1109/CEC.2003.1299412",

language = "English",

pages = "2572--2579",

note = "2003 Congress on Evolutionary Computation, CEC 2003 ; Conference date: 08-12-2003 Through 12-12-2003",

}

TY - CONF

T1 - Emergence of adaptive behaviors by redundant robots - Robustness to changes environment and failures

AU - Ito, K.

AU - Gofuku, A.

PY - 2003

Y1 - 2003

N2 - Acquiring adaptive behaviors of robots automatically is one of the most interesting topics of the evolutionary systems. In previous works, we have developed an adaptive autonomous control method for redundant robots. The QDSEGA is one of the methods that we have proposed for them. The QDSEGA is realized by combining Q-learning and GA, and it can acquire suitable behaviors by adapting a movement of a robot for a task. In this paper, we focus on the adaptability of the QDSEGA and discuss the robustness of the autonomous redundant robot that is controlled by the QDSEGA. To demonstrate the effectiveness of the QDSEGA, simulations of obstacle avoidance by a 10-link manipulator in the changeable environment and locomotion by a 12-legged robot with failures have been carried out, and as a result, adaptive behaviors for each environment and each broken body have emerged.

AB - Acquiring adaptive behaviors of robots automatically is one of the most interesting topics of the evolutionary systems. In previous works, we have developed an adaptive autonomous control method for redundant robots. The QDSEGA is one of the methods that we have proposed for them. The QDSEGA is realized by combining Q-learning and GA, and it can acquire suitable behaviors by adapting a movement of a robot for a task. In this paper, we focus on the adaptability of the QDSEGA and discuss the robustness of the autonomous redundant robot that is controlled by the QDSEGA. To demonstrate the effectiveness of the QDSEGA, simulations of obstacle avoidance by a 10-link manipulator in the changeable environment and locomotion by a 12-legged robot with failures have been carried out, and as a result, adaptive behaviors for each environment and each broken body have emerged.

UR - http://www.scopus.com/inward/record.url?scp=24144493368&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=24144493368&partnerID=8YFLogxK

U2 - 10.1109/CEC.2003.1299412

DO - 10.1109/CEC.2003.1299412

M3 - Paper

AN - SCOPUS:24144493368

SP - 2572

EP - 2579

T2 - 2003 Congress on Evolutionary Computation, CEC 2003

Y2 - 8 December 2003 through 12 December 2003

ER -

Emergence of adaptive behaviors by redundant robots - Robustness to changes environment and failures

Abstract

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this