Multi-objective parameter CPG optimization for gait generation of a biped robot

Oliveira, Miguel; Matos, Vitor; Santos, Cristina P.; Costa, Lino

doi:10.1109/icra.2013.6631012

Cited by 20 publications

(19 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides the above mentioned references, many others have tried to overcome this difficulty via applying search-based optimization methods. For example, Kim et al used Particle Swarm Optimization (PSO) to search the CPG parameters in order to generate optimal walk in a biped robot [29]; Oliveira et al applied an Evolutionary Algorithm (EV) to search for the optimal set of the CPG parameters for stable walking in a humanoid robot [30].…”

Section:  Optimization Methods To Design Cpg Networkmentioning

confidence: 99%

Gait Generation and Transition for Bipedal Locomotion System Using Morris-Lecar Model of Central Pattern Generator

2017

View full text Add to dashboard Cite

Abstract:In this paper, we intend to improve the CPG network presented by Pinto et al. based on 4-cell model for bipedal locomotion systems. This model is composed of four coupled identical cells which internal dynamics of each one is described by the Morris-Lecar nonlinear differential equation and the couplings between the cells follow the synaptic type. We exploit an elitist non-dominated sorting genetic algorithm (NSGA II) to find the best set of coupling weights by which the phase differences become optimally close to the ones required for a primary bipedal gait. Thus, we achieve the rhythmic signals associated with four primary bipedal gaits of walk, run, two-legged jump, and two-legged hop. Also, we successfully obtain all secondary gaits corresponding to the bipedal locomotion identified by Pinto et al. from the 4-cell model, by symmetry breaking bifurcations of primary gaits. Particularly, we are able to produce the secondary gait called "hesitation walk" through transition from primary gaits of run and two-legged jump.

show abstract

Section:  Optimization Methods To Design Cpg Networkmentioning

confidence: 99%

Gait Generation and Transition for Bipedal Locomotion System Using Morris-Lecar Model of Central Pattern Generator

2017

View full text Add to dashboard Cite

show abstract

“…In [25], it is also proposed a locomotion controller based in CPGs. They achieved a 8cm/s velocity from a hand tuned CPG parameterization in simulation, and were able to optimize the robot velocity to 10(cm/s) using the multi objective NSGA-II algorithm.…”

Section: Related Workmentioning

confidence: 99%

“…It was inspired from [25] and considered the following objectives: max(f D ), min(f F ) and max(f GC ). 10 experiments were performed and afterwards the transferability (f T ) for the 10 non-dominated sets of solutions were calculated.…”

Section: B Treatmentsmentioning

confidence: 99%

“…The initial population, of size n p , is generated out of a hand tuned solution which is known to be able to walk on the real robot [25]. b) All individuals p i ∈ P, i = {1, .…”

Section: Optimization Loopmentioning

confidence: 99%

“…Most typical approaches when implementing CPGs for bipedal walking use phase oscillators that are fed into pattern generation layers [21], [1], [3], [25] or using neural oscillators [19].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Optimization of humanoid walking controller: Crossing the reality gap

Oliveira

Doncieux

Mouret

et al. 2013

2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids)

Self Cite

View full text Add to dashboard Cite

Abstract-Humanoid locomotion remains a challenge because of the inherent instability of such robotic platforms. Inspired from observations on animals, Central Pattern Generators have been proposed to support the generation of rhythmic patterns able to make a robot smoothly walk while requiring few computational power. Nevertheless, tuning such controllers is challenging, in particular because small irregularities in the walking pattern easily make the robot fall. Optimization algorithms can be used to tune them in simulation, but the transfer of such solutions to the real robot raises the reality gap problem, as a solution efficient in simulation may well be inefficient in reality. It is proposed here to use the transferability approach to solve this problem. Its principle is to learn a model of the transferability between simulation and reality while doing several evaluations on the real robot. This model is then used to estimate how well a controller will transfer onto the real robot and the optimization process tries to optimize it besides other cost functions related to locomotion and tested in simulation only. The approach has been applied to the DARWIN-OP robot.

show abstract

Methods Synthesis of Central Pattern Generator Inspired Biped Walking Control

Liu

Chen

2015

Proceedings of the 2015 Chinese Intelligent Automation Conference

View full text Add to dashboard Cite

Bio-inspired locomotion control method is one of the ways to promote the site application of biped robots. This paper synthesizes the main idea and structure of central pattern generator (CPG) inspired biped walking control methods into two kinds of common strategies: joint space control methods and workspace control methods. The key problems of these two approaches are deeply explored. Finally, the research direction of the CPG-inspired control method is discussed. The motivation of this paper is to synthesize the current mainly methods for biped robots to present a practical guide to researchers and engineers interested in the CPG-inspired control approaches.

show abstract

Multi-objective parameter CPG optimization for gait generation of a biped robot

Cited by 20 publications

References 11 publications

Gait Generation and Transition for Bipedal Locomotion System Using Morris-Lecar Model of Central Pattern Generator

Gait Generation and Transition for Bipedal Locomotion System Using Morris-Lecar Model of Central Pattern Generator

Optimization of humanoid walking controller: Crossing the reality gap

Methods Synthesis of Central Pattern Generator Inspired Biped Walking Control

Contact Info

Product

Resources

About