Tactile object recognition using deep learning and dropout
By A. Schmitz, Yusuke Bansho, Kuniaki Noda, H. Iwata, Tetsuya Ogata, Shigeki Sugano. 2014
98 citations recorded by the source corpus.
Subfields: Biomedical Engineering, Cognitive Neuroscience, Control and Systems Engineering
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Biomedical Engineering
In Cognitive Neuroscience
In Control and Systems Engineering
Citations in the corpus
- A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation (2016, neutral): “used sensor information is also considered as the input for deep-learning model. Through tactile sensor on the end effector, object and material detection were also implemented through deep-learning (Schmitz et al., 2014; Baishya and Bauml, 2016). Valada et al. (2015) achieved terrain classification ”
- Deep-learning in Mobile Robotics - from Perception to Control Systems: A Survey on Why and Why not (2016, methodology): “Several reasonable training strategies like batch-normalization (Ioffe and Szegedy, 2015) and drop-out (Srivastava et al., 2014) also make a contribution to the deep-learning development.”
- Robotic Tactile Perception of Object Properties: A Review (2017, methodology): “Descriptors adapted from vision Extract distinct features; invariant to force and pose variance; can be used to share information with vision Some of the features are of high dimension compared to original reading; hard to design; predefined and hand-crafted Planar array sensors; low curvature senso”
- Deep learning in robotics: a review of recent research (2017, background): “Additionally, Schmitz et al. [88] studied tactile object recognition with a TWENDY-ONE multi-finger hand, which provides a multimodal set of 312 values from distributed skin sensors, fingertip forces, joint torques, actuator currents, and joint angles.”