Application of Neural Network to Nonlinear Static Decoupling of Robot Wrist Force Sensor

Lei, Jianhe; Qiu, Liankui; Liu, Ming; Song, Quanjun; Ge, Yaojun

doi:10.1109/wcica.2006.1714077

Cited by 4 publications

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There has been some prior work in employing machine learning techniques to improve sensor performance in the face of nonlinearities, disturbances or other detrimental effects. Neural networks have been used to approximate nonlinearities in multi-axis force sensors [7,8,9]. Artificial neural networks (ANN) have been employed to linearize the behavior of capacitive humidity sensors [10].…”

Section: Introductionmentioning

confidence: 99%

Machine learning approaches to environmental disturbance rejection in multi-axis optoelectronic force sensors

Gafford

Doshi‐Velez

Wood

et al. 2016

Sensors and Actuators A: Physical

View full text Add to dashboard Cite

Light-Intensity Modulated (LIM) force sensors are seeing increasing interest in the field of surgical robotics and flexible systems in particular. However, such sensing modalities are notoriously susceptible to ambient effects such as temperature and environmental irradiance which can register as false force readings. We explore machine learning techniques to dynamically compensate for environmental biases that plague multi-axis optoelectronic force sensors. In this work, we fabricate a multisensor: three-axis LIM force sensor with integrated temperature and ambient irradiance sensing manufactured via a monolithic, origami-inspired fabrication process called printed-circuit MEMS. We explore machine learning regression techniques to compensate for temperature and ambient light sensitivity using on-board environmental sensor data. We compare batch-based ridge regression, kernelized regression and support vector techniques to baseline ordinary least-squares estimates to show that on-board environmental monitoring can substantially improve sensor force tracking performance and output stability under variable lighting and large (>100C) thermal gradients. By augmenting the least-squares estimate with nonlinear functions describing both environmental disturbances and cross-axis coupling effects, we can reduce the error in F x , F y and F z by 10%, 33%, and 73%, respectively. We assess viability of each algorithm tested in terms of both prediction accuracy and computational overhead, and analyze kernel-based regression for prediction in the context of online force feedback and haptics applications in surgical robotics. Finally, we suggest future work for fast approximation and prediction using stochastic, sparse kernel techniques.

show abstract