Development of a full body multi-axis soft tactile sensor suit for life sized humanoid robot and an algorithm to detect contact states

Author(s):  
Iori Kumagai ◽  
Kazuya Kobayashi ◽  
Shunichi Nozawa ◽  
Yohei Kakiuchi ◽  
Tomoaki Yoshikai ◽  
...  
2011 ◽  
Vol 23 (2) ◽  
pp. 239-248 ◽  
Author(s):  
Shunichi Nozawa ◽  
◽  
Ryohei Ueda ◽  
Yohei Kakiuchi ◽  
Kei Okada ◽  
...  

The novel method we propose involves a humanoid robot manipulating objects of varying size and weight. How an object is manipulated is generally determined by size and weight. The motion generation system we developed 1) utilizes manipulation strategies defined by which contact points on the robot are to be used, 2) selects the adequate manipulation strategy based on the object, and 3) generates a full-body posture sequence for the humanoid robot with controlled reaction forces and full-body balance using the manipulation strategy as an initial condition. Our system enables the robot to manipulate an object of weight thanks to multiple strategies. Our method’s effectiveness is confirmed in experiments in which a humanoid robot manipulates six different types of objects.


2007 ◽  
Vol 2007 (0) ◽  
pp. _1A1-A02_1-_1A1-A02_4 ◽  
Author(s):  
Yoshiyuki OHMURA ◽  
Akihiko Nagakubo ◽  
Yasuo Kuniyoshi

Sensors ◽  
2021 ◽  
Vol 21 (18) ◽  
pp. 6024
Author(s):  
Somchai Pohtongkam ◽  
Jakkree Srinonchat

A tactile sensor array is a crucial component for applying physical sensors to a humanoid robot. This work focused on developing a palm-size tactile sensor array (56.0 mm × 56.0 mm) to apply object recognition for the humanoid robot hand. This sensor was based on a PCB technology operating with the piezoresistive principle. A conductive polymer composites sheet was used as a sensing element and the matrix array of this sensor was 16 × 16 pixels. The sensitivity of this sensor was evaluated and the sensor was installed on the robot hand. The tactile images, with resolution enhancement using bicubic interpolation obtained from 20 classes, were used to train and test 19 different DCNNs. InceptionResNetV2 provided superior performance with 91.82% accuracy. However, using the multimodal learning method that included InceptionResNetV2 and XceptionNet, the highest recognition rate of 92.73% was achieved. Moreover, this recognition rate improved when the object exploration was applied to demonstrate.


Sign in / Sign up

Export Citation Format

Share Document