Sampling-Based Nonlinear Stochastic Optimal Control for Neuromechanical Systems

Reed, Emily A.; Pereira, Marcus A.; Valero-Cuevas, Francisco J.; Theodorou, Evangelos A.

doi:10.1109/embc44109.2020.9175861

Cited by 2 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We argue, however, that they are important when controlling nonlinear systems like bio-inspired tendon-driven limbs. Improving the stability margin and robustness of optimal control methods for such systems has been a longstanding goal (Doyle, 1978 ; Weghe et al, 2004 ; Theodorou et al, 2011 ; Reed et al, 2020 ). Improving the joint angle estimates can only facilitate and improve their control.…”

Section: Discussionmentioning

confidence: 99%

insideOut: A Bio-Inspired Machine Learning Approach to Estimating Posture in Robots Driven by Compliant Tendons

et al. 2021

Self Cite

View full text Add to dashboard Cite

Estimates of limb posture are critical for controlling robotic systems. This is generally accomplished with angle sensors at individual joints that simplify control but can complicate mechanical design and robustness. Limb posture should be derivable from each joint's actuator shaft angle but this is problematic for compliant tendon-driven systems where (i) motors are not placed at the joints and (ii) nonlinear tendon stiffness decouples the relationship between motor and joint angles. Here we propose a novel machine learning algorithm to accurately estimate joint posture during dynamic tasks by limited training of an artificial neural network (ANN) receiving motor angles and tendon tensions, analogous to biological muscle and tendon mechanoreceptors. Simulating an inverted pendulum—antagonistically-driven by motors and nonlinearly-elastic tendons—we compare how accurately ANNs estimate joint angles when trained with different sets of non-collocated sensory information generated via random motor-babbling. Cross-validating with new movements, we find that ANNs trained with motor angles and tendon tension data predict joint angles more accurately than ANNs trained without tendon tension. Furthermore, these results are robust to changes in network/mechanical hyper-parameters. We conclude that regardless of the tendon properties, actuator behavior, or movement demands, tendon tension information invariably improves joint angle estimates from non-collocated sensory signals.

show abstract

Section: Discussionmentioning

confidence: 99%