Dynamic Recurrent Neural Network for Biped Robot Equilibrium Control: Preliminary Results

Scesa, Vincent; Mohamed, B.; Hénaff, Patrick; Ouezdou, Fethi Ben

doi:10.1109/robot.2005.1570751

Cited by 2 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The difference between the force shapes in the two periods represents the compensation brought about by the mass motion. In a previous study (Scesa, Mohamed, Henaff & Ouezdou, 2005), it was shown that neural control brings a decrease of about 50% in the measured forces on each axis.…”

Section: External Disturbance Compensation After Learningmentioning

confidence: 92%

See 1 more Smart Citation

Real time implementation of CTRNN and BPTT algorithm to learn on-line biped robot balance: Experiments on the standing posture

Hénaff

Scesa²,

Ouezdou³

et al. 2011

Control Engineering Practice

View full text Add to dashboard Cite

This paper describes experimental results regarding the real time implementation of continuous time recurrent neural networks (CTRNN) and the dynamic back-propagation through time (BPTT) algorithm for the on-line learning control laws. Experiments are carried out to control the balance of a biped robot prototype in its standing posture. The neural controller is trained to compensate for external perturbations by controlling the torso's joint motions. Algorithms are embedded in the real time electronic unit of the robot. On-line learning implementations are presented in detail. The results on learning behavior and control performance demonstrate the strength and the efficiency of the proposed approach.

show abstract

Section: External Disturbance Compensation After Learningmentioning

confidence: 92%

“…Several contributions in this area have already been published (see Scesa, Mohamed, Henaff, & Ouezdou, 2005). This paper focuses on describing the real time implementation of the learning algorithms embedded into the robot control unit.…”

Section: Introductionmentioning

confidence: 99%