Satoshi Funabashi 교수

Multi-fingered hands could be used to achieve many dexterous manipulation tasks, similarly to humans, and tactile sensing could enhance the manipulation stability for a variety of objects. However, tactile sensors on multi-fingered hands have a variety of sizes and shapes. Convolutional neural networks (CNN) can be useful for processing tactile information, but the information from multi-fingered hands needs an arbitrary pre-processing, as CNNs require a rectangularly shaped input, which may lea

This paper investigates tactile object recognition with relatively densely distributed force vector measurements and evaluates what kind of tactile information is beneficial for object recognition. The uSkin tactile sensors are embedded in an Allegro Hand, and provide 240 triaxial force vector measurements in total in all fingers. Active object sensing is used to gather time-series training and testing data. A simple feedforward, a recurrent, and a convolutional neural network are used for recog

Distributed tactile sensors on multi-fingered hands can provide high-dimensional information for grasping objects, but it is not clear how to optimally process such abundant tactile information. The current paper explores the possibility of using a morphology-specific convolutional neural network (MS-CNN). uSkin tactile sensors are mounted on an Allegro Hand, which provides 720 force measurements (15 patches of uSkin modules with 16 triaxial force sensors each) in addition to 16 joint angle meas

Multifingered robot hands can be extremely effective in physically exploring and recognizing objects, especially if they are extensively covered with distributed tactile sensors. Convolutional neural networks (CNNs) have been proven successful in processing high dimensional data, such as camera images, and are, therefore, very well suited to analyze distributed tactile information as well. However, a major challenge is to organize tactile inputs coming from different locations on the hand in a c

Moving objects within the hand is challenging, especially if the objects are of various shape and size. In this paper we use machine learning to learn in-hand manipulation of such various sized and shaped objects. The TWENDY-ONE hand is used, which has various properties that makes it well suited for in-hand manipulation: a high number of actuated joints, passive degrees of freedom and soft skin, six-axis force/torque (F/T) sensors in each fingertip, and distributed tactile sensors in the skin.

The use of tactile information is one of the most important factors for achieving stable in-grasp manipulation. Especially with low-cost robotic hands that provide low-precision control, robust in-grasp manipulation is challenging. Abundant tactile information could provide the required feed-back to achieve reliable in-grasp manipulation also in such cases. In this research, soft distributed 3-axis skin sensors ("uSkin") and 6-axis F/T (force/torque) sensors were mounted on each fingertip of an

Performing various in-hand manipulation tasks, without learning each individual task, would enable robots to act more versatile, while reducing the effort for training. However, in general it is difficult to achieve stable in-hand manipulation, because the contact state between the fingertips becomes difficult to model, especially for a robot hand with anthropomorphically shaped fingertips. Rich tactile feedback can aid the robust task execution, but on the other hand it is challenging to proces

In past research, in-hand object manipulation for various sized and shaped objects has been achieved. However, the network had to be trained for each different motion. Training data takes time to acquire and increases the hardware load, thereby increasing the cost for training data. Four-fingered in-hand manipulation is especially difficult as a high number of joints need to be controlled in synchrony. This paper presents a method that reduces the required training data for in-hand manipulation

Changing the grasping posture of objects within a robot hand is hard to achieve, especially if the objects are of various shape and size. In this paper we use a neural network to learn such manipulation with variously sized and shaped objects. The TWENDY-ONE hand possesses various properties that are effective for in-hand manipulation: a high number of actuated joints, passive degrees of freedom and soft skin, six-axis force/torque (F /T) sensors in each fingertip and distributed tactile sensors

Object picking with two-fingered grippers is widely used in practice. However, the deformability and slipperiness of the target object still remain a challenge, and not resolving them might lead to breaking or dropping of the grasped objects. To prevent such instances, tactile sensing plays an important role because it can directly detect even the subtle changes that occur during grasping. Mechanoreceptors in the human skin detect such events by the change in the skin shape and/or vibration. Usi

To achieve a desired grasping posture (including object position and orientation), multi-finger motions need to be conducted according to the the current touch state. Specifically, when subtle changes happen during correcting the object state, not only proprioception but also tactile information from the entire hand can be beneficial. However, switching motions with high-DOFs of multiple fingers and abundant tactile information is still challenging. In this study, we propose a loss function with

This article presents feature extraction with deep learning for in-hand manipulation. It is important that robot hands can manipulate different sized and shaped objects. In order to generate versatile manipulation with such objects, we used deep learning to extract critical information from object manipulating motions.

This paper presents generating some manipulations with soft skin on fingertips by interpolation control. In the aging society, symbiotic robots are expected and need to have versatile robot hands. In the conventional researches, active and passive flexibility were featured to adapt to actual situations in daily life and high-quality robot hand systems were developed. However, such robot hands are too hard to maintain or use in actual situations because of its taskspecified models and complicated

Various objects were successfully manipulated in our previous research. However, the network had to be trained for each different motion. Therefore, there is a hardware load for getting training data for each motion. Specifically, four-fingered in-hand manipulation is difficult to control because of a high number of joints. This paper suggests a method that reduces the required training data for in-hand manipulation with the concept of pre-training and mutual finger motions. The training data in

Distributed tactile sensing with multi-fingered hands can provide high-dimensional information for grasping objects but it is not clear how to optimally process such abundant tactile information. The current paper explores the possibility of using a morphology-specific convolutional neural network (MS-CNN). In particular, uSkin tactile sensors are mounted on an Allegro Hand, which provide 720 force measurements in addition to 16 joint angle measurements. Consecutive layers in the CNN get input f