Predictive Uncertainty Estimation Using Deep Learning for Soft Robot Multimodal Sensing

Ding, Ze Yang; Loo, Junn Yong; Baskaran, Vishnu Monn; Nurzaman, Surya G.; Tan, Chee Pin

doi:10.1109/lra.2021.3056066

Cited by 14 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors of [11] illustrate that LSTM outperforms an analytical model in control tasks. Also, LSTM is employed in [12] on a soft pneumatic finger for contact position and force estimation. LSTM in [13] estimates finger motion and contact force, and this paper shows that the estimation accuracy will improve with more sensing channels.…”

Section: A Neural Network Controllers For Soft Robotsmentioning

confidence: 99%

A Hybrid Adaptive Controller for Soft Robot Interchangeability

Chen,

Ren,

Bernabei

et al. 2024

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Soft robots have been leveraged in considerable areas like surgery, rehabilitation, and bionics due to their softness, flexibility, and safety. However, it is challenging to produce two same soft robots even with the same mold and manufacturing process owing to the complexity of soft materials. Meanwhile, widespread usage of a system requires the ability to replace inner components without highly affecting system performance, which is interchangeability. Due to the necessity of this property, a hybrid adaptive controller is introduced to achieve interchangeability from the perspective of control approaches. This method utilizes an offline-trained recurrent neural network controller to cope with the nonlinear and delayed response from soft robots. Furthermore, an online optimizing kinematics controller is applied to decrease the error caused by the above neural network controller. Soft pneumatic robots with different deformation properties but the same mold have been included for validation experiments. In the experiments, the systems with different actuation configurations and the different robots follow the desired trajectory with errors of 3.3 ± 2.9% and 4.3 ± 4.1% compared with the working space length, respectively. Such an adaptive controller also shows good performance on different control frequencies and desired velocities. This controller is also compared with a model-based controller in simulation. This controller endows soft robots with the potential for wide application, and future work may include different offline and online controllers. A weight parameter adjusting strategy may also be proposed in the future.

show abstract

Section: A Neural Network Controllers For Soft Robotsmentioning

confidence: 99%

A Hybrid Adaptive Controller for Soft Robot Interchangeability

Chen,

Ren,

Bernabei

et al. 2024

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…We have been inspired by recent work leveraging deep learning to interpret various types of non-magnetic sensor data for proprioception purposes. [19][20][21][22] However, learning end-to-end mappings from sensors to configurations has three significant drawbacks: (i) it is data-intensive, (ii) it calls for recurrent architectures to encourage temporal consistency for the robot's configuration estimates, (iii) it requires re-training when changing the kinematic model of the robot. We propose a neural architecture that circumvents all three issues (see Fig.…”

Section: Introductionmentioning

confidence: 99%

Learning 3D shape proprioception for continuum soft robots with multiple magnetic sensors

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Manipulators are very common automation equipment in daily life, which is widely used in industrial production, 1 construction, medical and health, 2 aerospace, 3 deep sea exploration and other fields. Because of their good stability, and save manpower, they also have a significant impact on social and economic development.…”

Section: Introductionmentioning

confidence: 99%

Fixed‐time fault‐tolerant control of manipulator systems based on sliding mode observer

Li,

Chen,

Peng

et al. 2023

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

A fixed‐time fault‐tolerant control scheme based on sliding mode observer is proposed, which makes the system more stable and stronger anti‐jamming ability. In our design, its distinct characteristic is to combine the passive fault‐tolerant control and non‐singular fast terminal sliding mode (NFTSM). And it ensures that the system states can converge to a very small neighborhood near the equilibrium point in a fixed time no matter in normal condition or fault condition. In addition, a novel sliding‐mode observer and a fast variable power reaching law are added to make the system converge faster and chattering smaller. Finally, the computer simulation results of a two‐joint manipulator demonstrate the feasibility of the proposed strategy.

show abstract

Predictive Uncertainty Estimation Using Deep Learning for Soft Robot Multimodal Sensing

Cited by 14 publications

References 19 publications

A Hybrid Adaptive Controller for Soft Robot Interchangeability

A Hybrid Adaptive Controller for Soft Robot Interchangeability

Learning 3D shape proprioception for continuum soft robots with multiple magnetic sensors

Fixed‐time fault‐tolerant control of manipulator systems based on sliding mode observer

Contact Info

Product

Resources

About