Three-Fingers FBG Tactile Sensing System Based on Squeeze-and-Excitation LSTM for Object Classification

Lyu, Chengang; Yang, Bo; Tian, Jiachen; Jin, Jie; Ge, Chunfeng; Yang, Jiachen

doi:10.1109/tim.2022.3181290

Cited by 13 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lyu et al pasted three FBGs in the middle of a flexible finger as the tactile sensor and combined with the Faraday rotator mirror to classify six different objects of similar size and shape with an accuracy of 95.97%. 14 In addition, the robotic grippers with vision sensors are widely used to recognize and grasp objects. A. Beyhan et al used a low-cost four-DOF robotic arm and Kinect camera to detect and capture target objects in the scene.…”

Section: Introductionmentioning

confidence: 99%

Rotary robotic gripper with LiDAR-tactile sensor fusion

Wang,

Jia,

Yan

et al. 2023

Opt. Eng.

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Rotary robotic gripper with LiDAR-tactile sensor fusion

Wang,

Jia,

Yan

et al. 2023

Opt. Eng.

View full text Add to dashboard Cite

“…In addition, the high-dimensional fully connected layer output can cause overfitting on the training data, which results in reduced localization accuracy. To deal with this problem, Lyu et al [43] proposed a three-finger FBG haptic sensing system based on wavelength-scanning optical coherence tomography. The high-dimensional tactile signals are demodulated into time-dependent sequences using the long short-term memory network (LSTM) model modified by the recurrent neural network (RNN) model [44,45].…”

Section: Introductionmentioning

confidence: 99%

An End‐to‐End Robotic Visual Localization Algorithm Based on Deep Learning

Chen,

Wang,

Fan

et al. 2023

Journal of Sensors

View full text Add to dashboard Cite

Efficient localization plays a significant role in mobile autonomous robots’ navigation systems. Traditional visual simultaneous localization systems based on point feature matching suffer from two shortcomings. First one is that the method of tracking features is not robust for environments with frequent changes in brightness. Another one is the large of consecutive visual keyframes can consume expensive computational and storage resources in complex environments. To solve these problems, an end-to-end real-time six degrees of freedom object pose estimation algorithm is proposed to solve the robust and efficient challenges through a deep learning model. First, preprocessing operations such as cropping, averaging, and timestamp alignment are performed on datasets to reduce computational cost and time. Second, the processed dataset is fed into our neural network model to extract the most effective features for matching. Finally, the robot’s current 3D translation and 4D angle information are predicted and output to achieve an end-to-end localization system. A broad range of experiments are performed on both indoor and outdoor datasets. The experimental results demonstrate that the translation and orientation accuracy in outdoor scenes improved by 32.9% and 31.4%, respectively. The average improvement of localization accuracy in indoor scenes is 38.4%, and the angle improvement is 13.1%. Moreover, the effectiveness of predicting the global motion trajectories of sequential images algorithm has been verified and is superior to other convolutional neural network methods.

show abstract

An End-to-End Robotic Visual Localization Algorithm Based on Deep Learning

Wang

Chen

Fan

et al. 2023

2023 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Efficient localization plays a significant role in mobile autonomous robots' navigation systems. Traditional visual simultaneous localization systems based on point feature matching suffer from two shortcomings. First one is that the method of tracking features is not robust for environments with frequent changes in brightness. Another one is the large of consecutive visual keyframes can consume expensive computational and storage resources in complex environments. To solve these problems, an end-to-end real-time six degrees of freedom object pose estimation algorithm is proposed to solve the robust and efficient challenges through a deep learning model. First, preprocessing operations such as cropping, averaging, and timestamp alignment are performed on datasets to reduce computational cost and time. Second, the processed dataset is fed into our neural network model to extract the most effective features for matching. Finally, the robot's current 3D translation and 4D angle information are predicted and output to achieve an end-to-end localization system. A broad range of experiments are performed on both indoor and outdoor datasets. The experimental results demonstrate that the translation and orientation accuracy in outdoor scenes improved by 32.9% and 31.4%, respectively. The average improvement of localization accuracy in indoor scenes is 38.4%, and the angle improvement is 13.1%. Moreover, the effectiveness of predicting the global motion trajectories of sequential images algorithm has been verified and is superior to other convolutional neural network methods.

show abstract

Three-Fingers FBG Tactile Sensing System Based on Squeeze-and-Excitation LSTM for Object Classification

Cited by 13 publications

References 31 publications

Rotary robotic gripper with LiDAR-tactile sensor fusion

Rotary robotic gripper with LiDAR-tactile sensor fusion

An End‐to‐End Robotic Visual Localization Algorithm Based on Deep Learning

An End-to-End Robotic Visual Localization Algorithm Based on Deep Learning

Contact Info

Product

Resources

About