With the increasing use of robots in every sphere of life, it becomes utmost important to establish proper communication between humans and robots.
A team of researchers of Speech and Audio (SAG) at Indian Institute of Science (IISC), Bengaluru have been working towards enhancing Human and Robot communication to which they call it as ‘HUBOT’. The research aims to obtain better response from robots to given commands. This team is led by Dr. T.V Sreenivas, Professor at the Department of Electronics and Communication Engineering. He leads the research activities of SAG.
There are different kinds of robots with different programmes. While human beings can differentiate between various sounds, it is difficult for robots to do the same. This is a major obstacle in human-robot interactions.
The researchers are actively engaged in enhancing Hubot communication. The techniques used to enable Hubot communication includes voice and word recognition and gross localisation of sound.
The setup required to effectively capture the data needed involves the use of multiple microphones which are used to capture the data from the surrounding environment after which it will be processed in a suitable form to give the required response to the robot.
The team has developed several techniques which work to make Hubot communication more effective. One of these is the Y-Array technique which works in an indoor environment to localise and track moving source. Another technique involves the use of multiple rotating microphones on the robot. This method has given satisfactory results which have further enhanced the efficiency of HUBOT communication.
Digital Signal Processing techniques and properties of speech signals are studied by the SAG in order to overcome the existing difficulties in human-robot voice based interactions. A lot of processing steps are involved to make the robot behave in a certain way in the considered environment and the foremost step is to analyse real life situation or physical problem faced by it after which it will convert problem into mathematical form and written as algorithm.
The team is working on challenges which must be addressed before Hubot can be considered perfect.
A team of researchers of Speech and Audio (SAG) at Indian Institute of Science (IISC), Bengaluru have been working towards enhancing Human and Robot communication to which they call it as ‘HUBOT’. The research aims to obtain better response from robots to given commands. This team is led by Dr. T.V Sreenivas, Professor at the Department of Electronics and Communication Engineering. He leads the research activities of SAG.
There are different kinds of robots with different programmes. While human beings can differentiate between various sounds, it is difficult for robots to do the same. This is a major obstacle in human-robot interactions.
The researchers are actively engaged in enhancing Hubot communication. The techniques used to enable Hubot communication includes voice and word recognition and gross localisation of sound.
The setup required to effectively capture the data needed involves the use of multiple microphones which are used to capture the data from the surrounding environment after which it will be processed in a suitable form to give the required response to the robot.
The team has developed several techniques which work to make Hubot communication more effective. One of these is the Y-Array technique which works in an indoor environment to localise and track moving source. Another technique involves the use of multiple rotating microphones on the robot. This method has given satisfactory results which have further enhanced the efficiency of HUBOT communication.
Digital Signal Processing techniques and properties of speech signals are studied by the SAG in order to overcome the existing difficulties in human-robot voice based interactions. A lot of processing steps are involved to make the robot behave in a certain way in the considered environment and the foremost step is to analyse real life situation or physical problem faced by it after which it will convert problem into mathematical form and written as algorithm.
The team is working on challenges which must be addressed before Hubot can be considered perfect.