Fig 1 - uploaded by Takashi Kuremoto
Content may be subject to copyright.
Source publication
Feeling and emotion are important to human being during his/her learning process, also valuable to be adopted into intelligent machines. This research presents a system which forms and expresses feelings of a robot. The vision information of robot is used and the environment features are categorized by a hierarchical SOM (Self-Organization Map). Th...
Similar publications
Our long-term goal is to develop autonomous robotic systems that have the cognitive abilities of humans, including communication, coordination, adapting to novel situations, and learning through experience. Our approach rests on the recent integration of the Soar cognitive architecture with both virtual and physical robotic systems. Soar has been u...
The optimization of existing manufacturing systems is a challenging and highly complex task, requiring high-quality information about the current system. Currently, acquiring such information involves tedious and to a large extend manual work. In this paper we present an ongoing joint project effort bringing together cognitive robotics and planning...
The goal of the CoSy project is to create cognitive robots to serve as a testbed of theories on how humans work (13), and to identify problems and techniques relevant to producing general-purpose human- like domestic robots. Given the constraints on the resources available at the robot's disposal and the complexity of the tasks that the robot has t...
In teleoperation tasks, information about the relative posture between end-effector and the object to be grasped is of key importance for human operators. Although visual information plays a major role in monitoring collision and fun-tuning the end-effector towards the object, the operator should make strict observations about the video images to t...
Citations
... The topics that emerged under this umbrella related to designing cost-effective affective robots, emotion core for autonomous robots, robotic control architecture based on emotions, affective movement features of robots, nonverbal emotional interaction for robots, computation mechanism for robot emotions, etc. Among these studies, Kuremoto et al. (2007) present a system forming and expressing the feelings of a robot, while Suguitan et al. (2020) developed a method for modifying emotive robot movements. ...
... To express the degree of how an instruction is learned by robot, a Feeling map which has the same number of units with Action map is designed as the output layer of the learning system as shown in Fig. 4. Feeling map expresses instruction recognition rate, i.e., the feeling of robot: more successful, happier it is. Feelings of partner robots, such as pet robots, entertainment robots, and so on, are important for human-machine interaction (HMI) when they are able to express vividly by their face expressions [19]. The distance between input pattern and units on Feature map and the reward from instructor are used to calculate feeling values which is normalized in [-1.0, 1.0] where high positive value means happiness and 0.0 is the initial value of each unit here. ...
In this paper, a novel self-organizing map (SOM) named "One-D-R-A-G-SOM" is proposed. It is a kind of one dimensional ring type growing SOM using asymmetric neighborhood function. As the topology of one dimensional ring type feature map is more suitable to increase or decrease the number of units, and the disorder of the map is available to be solved by the asymmetric neighborhood function, the proposed model gives priority of learning performance to the conventional two dimensional growing SOM. Additionally, One-D-R-A-G-SOM is introduced to a hand shape recognition and instruction learning system. Experiment results showed the effectiveness of the novel system comparing with systems using the conventional SOMs.
... To express the degree of how an instruction is learned by robot, a Feeling map which has the same number of units with Action map is designed as the output layer of the learning system as shown in Fig. 4. Feeling map expresses instruction recognition rate, i.e., the feeling of robot: more successful, happier it is. Feelings of partner robots, such as pet robots, entertainment robots, and so on, are important for humanmachine interaction (HMI) when they are able to express vividly by their face expressions [14]. The distance between input pattern and units on Feature map and the reward from instructor are used to calculate feeling values which is normalized in [-1.0, 1.0] where high positive value means happiness and 0.0 is the initial value of each unit here. ...
... Skin area in the image captured by a CCD camera needs to be extracted and regularized at first. For a frame of image in RGB format, it is transformed to HSV format at first, then, using the threshold values of Hue (H), and Saturation (S) [21] and Red (R) [13] [14][18] threshold in RGB, skin area is extracted as a binary image. Noise elimination and holes filling are also effective to segment a hand area from the binary image. ...
An asymmetric neighborhood function was proposed by Aoki and Aoyagi to instead of symmetric neighborhood function in conventional Kohonen's self-organizing map (SOM) to avoid topological twist of the order of units during training process. Meanwhile, a one dimensional ring type growing SOM was proposed by Ohta and Saito to reduce the unnecessary increasing of units of conventional 2-D growing SOM. In this paper, we adopt the asymmetric neighborhood to a parameterless growing SOM (PL-G-SOM) proposed by Kuremoto et al. to construct a novel SOM: One dimensional ring type growing SOM using asymmetric neighborhood function (One-D-R-A-G-SOM). The proposed SOM is applied to instruction recognition and learning system with input of hand shapes for human-machine-interaction (HMI), especially for users of speech handicapped people. The effectiveness of the proposed method was confirmed by the experiments comparing with systems using conventional SOMs.
... The distance from input pattern to BMU of Feature Map and the reward from instructor are used to calculate feeling values which is normalized in [-1.0, 1.0] where high positive value means happiness and 0.0 is the initial value of each unit. The learning algorithm is used as same as [17], also used in [10] and [11] so we do not describe it in detail here. ...
Learning and relearning ability is important to partner robots. From this point of view, here we propose an intelligent learning system with voice instruction recognition and action learning function. Transient-SOM (T-SOM), an advanced self-organizing map proposed by our previous work for hand gesture recognition and memorization is adopted and improved to be Parameter-Less T-SOM (PL-T-SOM) with an annealing plan. Learning and additional learning experiments used instructions in multiple languages including Japanese, English, Chinese and Malaysian showed the effectiveness of our proposed system.
Conventionally, human instructions to a robot are often given by previously designed signals such as voices and images. In this study, one's own "shapes of a hand" is suggested to be instructions in the human-machine interaction system. We proposed a Self-Organizing Map (SOM) with a memory layer named Transient-SOM (T-SOM) and adopted it to a hand image instruction learning system. In this study, instead of T-SOM, an improved SOM, Parameter-Less Growing Self-Organizing Map (PL-G-SOM) is used to improve the hand image instruction learning system. In order to verify the performance of the proposed system, comparison experiments were executed and the results showed the priorities of the new system.
For Human–Machine Interaction systems, it is a convenient method to send user׳s instructions to robots, TV sets, and other electronic equipments by showing different shapes of a hand of user. In our previous works, we proposed to use improved Kohonen׳s Self-Organizing Maps (SOMs), i.e., Transient-SOM (T-SOM) and Parameterless Growing SOM (PL-G-SOM) to recognize different patterns of hand shapes given by different bendings of five fingers of a hand. Recently, an asymmetric neighborhood function was proposed and introduced into the conventional SOM to improve the learning performance by Aoki and Aoyagi. In this paper, we propose to employ their asymmetric neighborhood function into Growing SOM (GSOM), which is an improved SOM to deal with additional online learning for input data. Furthermore, the improved GSOM is applied to a hand shape recognition and instruction learning system, and the results of experiments with eight kinds of instructions showed the effectiveness of the proposed system.
This paper proposes a voice command learning system for partner robots acquiring communication ability with instructors. Parameter-less Growing Self-Organizing Map (PL-G-SOM), an intelligent pattern recognition model given by our previous work, is used and computational feeling of robots is also adopted to improve the human-machine interaction system. AIBO robot was used in the experiment and the results of real environment showed the effectiveness of the proposed methods.
