Object recognition through human-robot interaction by speech

Kurnia, Rahmadi; Hossain, Altab; Nakamura, Akio; Kuno, Yoshinori

doi:10.1109/roman.2004.1374833

Cited by 16 publications

(19 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are 256 gray levels in an 8 bit gray scale image, and the intensity of each pixel can have from 0 to 255, with 0 being black and 255 being white. The gray scale of RGB was obtained by determining the average of each pixel as follows [8]:…”

Section: Icose Conference Proceedingsmentioning

confidence: 99%

Efficient Mixer in Baking “Galamai” Process by Using Camera Sensor

Kurnia¹

2016

KEG

View full text Add to dashboard Cite

One of Indonesian traditional food, expecially in Minangkabau called galamai was baked with inefficient and complicated manner. At least 4 or 5 person were needed to mix 30 kg galamai batter for 6 hours during baking process. This research solved those problems. The aim of this work was to displace a human labor with an automatic machine to make it more efficient. The basic idea of this reseach is to desain an automatic mixer by using camera sensor for controling the speed of DC machine. This mixer was worked base on the fact galamai batter characteristics that its color and viscosity will change during cooking process. Discoloration in galamai batter will be captured by camera sensor as a data input. Images data of the color of galamai batter will be converted in grayscale images. The intensity of gray scale image became an input for FIS (Fuzzy Inference System) which controled the speed of machine. The speed of motor will increase when the grayscale color of galamai batter is low. The system could controlled turning speed of motor automatically with acuration of speed value is more than 96.4% and synchronized in variation of galamai batter volume.

show abstract

Section: Icose Conference Proceedingsmentioning

confidence: 99%

Efficient Mixer in Baking “Galamai” Process by Using Camera Sensor

Kurnia¹

2016

KEG

View full text Add to dashboard Cite

show abstract

“…Most practical acoustic source localization schemes are based on time delay of arrival estimation for the following reasons: such systems are conceptually simple. They are reasonably effective in reverberant environment [3]. Moreover, their low computational complexity makes them well-suited to real-time implementation with several sensors.…”

Section: Mending Robot Hearing Localization Systemmentioning

confidence: 99%

Design of Mending Robot Based on Hearing and Virtual Reality

Yuan

Zhang

2008

2008 International Conference on Computer Science and Software Engineering

View full text Add to dashboard Cite

A novel mending robot is designed in this paper. The system consists of a robot which has a microphone array corresponding to human's ears and a virtual reality robot teleoperation system. Leaky point localization is realized based on time delay of arrival (TDOA) estimation using robot hearing. The robot can get to the leaky point and mend leaky chemistry container via virtual reality teleoperation system. Virtual robot and virtual environment are set up according to the real scene. Virtual robot is the agent of the real robot. Data glove is used to operate the virtual robot to complete the control towards the real robot. It can make the operator control the real robot to find the leaky point fast and conveniently. The system was tested in chemistry factory: robot could find the leaky point successfully and accomplish the mending task smoothly. A great deal of experiments prove that this robot mending system is reliable and efficient.

show abstract

“…Multimodal interfaces [1][12] [13] are considered strong candidates. Thus, we have been developing a helper robot that carries out tasks ordered by the user through voice and/or gestures [9][15] [18] [19]. In addition to gesture recognition, such robots need to have vision systems that can recognize the objects mentioned in speech.…”

Section: Introductionmentioning

confidence: 99%

“…It is, however, difficult to realize vision systems that can work in various conditions. Thus, we have proposed to use the human user's assistance through speech [9][15] [18] [19]. When the vision system cannot achieve a task, the robot makes a question to the user so that the natural response by the user can give helpful information for its vision system.…”

Section: Introductionmentioning

confidence: 99%

Interactive vision to detect target objects for helper robots

Hossain

Kurnia

Nakamura

et al. 2005

Proceedings of the 7th International Conference on Multimodal Interfaces

View full text Add to dashboard Cite

An effective human-robot interaction is essential for wide penetration of service robots into the market. Such robots need vision systems to recognize objects. It is, however, difficult to realize vision systems that can work in various conditions. More robust techniques of object recognition and image segmentation are essential. Thus, we have proposed to use the human user's assistance for object recognition through speech. The robot asks a question to which the user can easily answer and whose answer can efficiently reduce the number of candidate objects even if there are occluded objects and/or objects composed of multicolor parts in the scene. It considers the characteristics of features used for object recognition such as the easiness for humans to specify them by word, thus generating a user-friendly and efficient sequence of questions. Experimental results show that the robot can detect target objects by asking the questions generated by the method.

show abstract

Object recognition through human-robot interaction by speech

Cited by 16 publications

References 9 publications

Efficient Mixer in Baking “Galamai” Process by Using Camera Sensor

Efficient Mixer in Baking “Galamai” Process by Using Camera Sensor

Design of Mending Robot Based on Hearing and Virtual Reality

Interactive vision to detect target objects for helper robots

Contact Info

Product

Resources

About