Natural motion trajectory generation of biped locomotion robot using genetic algorithm through energy optimization

Arakawa, T.; Fukuda, Takahiro

doi:10.1109/icsmc.1996.571368

Cited by 32 publications

(17 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[7][8][9] The GA treats bitstrings or other data structures as genomes or chromosomes. A GA generally starts with a population of randomly generated bitstrings (genomes, individuals).…”

Section: Optimization Using a Gamentioning

confidence: 99%

Posture optimization for a humanoid robot using a simple genetic algorithm

Choi

Hong

2010

Int. J. Precis. Eng. Manuf.

View full text Add to dashboard Cite

NOMENCLATURE v J = Jacobian linear velocity ϖ J = Jacobian angular velocity A B P = position vector of {B} with respect to {A} A B R = rotation matrix of {B} with respect to {A} i j θ = joint angle of the robot where i = 1 for right foot, i = 2 for left foot, i = 3 for right arm, i = 4 for left arm, and j is the joint number (j = 1, … , 6) B Θ = rotation vector of robot center of gravity (COG) B P = position vector of robot COG e i Θ = rotation vector of palms and soles of the robot where i = 1 for right palm, i = 2 for left palm, i = 3 for right sole, and i = 4 for left sole e i P = position vector of palms and soles of the robot where i =1 for right palm, i = 2 for left palm, i = 3 for right sole, and i = 4 for left soleThis study proposes a method of real-time posture optimization of humanoid robots using a genetic algorithm and neural network. Here, the motion of a humanoid robot pushing an object is considered. When the robot starts pushing the object, the palms of its hands and the soles of its feet are assumed to be fixed on the object and on the ground, respectively, and they sense the reaction force from those surfaces. The reaction force results in changes of torques in the joints. This study determines an optimized posture using a genetic algorithm such that either the torques are evenly distributed over all joints or the torque of the weakest joint is rapidly reduced. Several different optimized postures are then generated by varying the reaction forces at the palms and the soles. The data is used as training patterns for a multilayer perceptron neural network with a back-propagation learning algorithm.Using the trained neural network, the humanoid robot can find the optimal posture for different reaction forces in real time. Several simulations were conducted to confirm the effectiveness of the proposed method. The simulation results showed that the proposed method can be used for real-time posture optimization of humanoid robots.

show abstract

“…[7][8][9] The GA treats bitstrings or other data structures as genomes or chromosomes. A GA generally starts with a population of randomly generated bitstrings (genomes, individuals).…”

Section: Optimization Using a Gamentioning

confidence: 99%

Posture optimization for a humanoid robot using a simple genetic algorithm

Choi

Hong

2010

Int. J. Precis. Eng. Manuf.

View full text Add to dashboard Cite

show abstract

“…For example, Capi et al (2002) have applied a GA to generate an optimal trajectory for a bipedal robot walking. Cabodevila and Abba (1997) designed optimal gait of biped robot based on expansion of the joint trajectories by Fourier's series using a GA. Arakawa and Fukuda (1996) used a GA to generate natural motion of biped locomotion with energy optimization.…”

Section: Introductionmentioning

confidence: 99%

Nearly optimal neural network stabilization of bipedal standing using genetic algorithm

Ghorbani¹,

Wu²,

Wang³

2007

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

“…Incremental ES differs from regular ES and GA because the search space is divided into smaller parts and evolved separately (Torresen, 1998) , (De Jong & Potter, 1995). By gradually evolving each task in series increased complexity can be achieved (Floreano & Mondada, 1998), (Arakawa & Fukuda, 1996). The first incremental approach was to first evaluate the leg position bits, with fixed pause lengths.…”

Section: The Incremental Es Approachmentioning

confidence: 99%

“…For instance, Hornby et al used genetic algorithms (GA) to generate robust gaits on the Aibo quadruped robot (Hornby et al, 2000). GA applied to bipedal locomotion was also proposed by Arakawa and Fukuda (Arakawa & Fukuda, 1996) who made a GA based on energy optimization in order to generate a natural, human-like bipedal gait. One of the main objections to applying EA's in the search for gaits is the time consuming characteristic of these techniques due to the large fitness search space that is normally present.…”

Section: Introductionmentioning

confidence: 99%