With the advancement in technology, a variety of robots are available today, each having their own, unique applications. Besides their usual implementations, robots are now being increasingly used for a wider range of applications from surgery and to welding. As the use and requirement for robots increases, it becomes essential that the communication between humans and robots also become efficient. ‘HUBOT’ is a term coined by the Speech and Audio Group (SAG) at the Indian Institute of Science (IISc), Bengaluru to represent any effective interaction which occurs between a Human and Robot. The team of researchers at IISc are actively working towards enhancing HUBOT communication, in order 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, IISc. He heads the Speech and Audio Group and is leading its research activities. Achieving an effective means of communication with these robots, however, is still problematic. Robots are rugged and programmable; this means that they can be made to follow a set of predefined commands easily. But, communicating effectively with robots poses many problems. It is difficult for a robot to accurately analyse and follow voice commands given by its master.
During human-human interactions, multiple sounds are simultaneously processed by our brain and we still segregate the sound containing the information we want. This is not the case with robots; they are unable to differentiate various sounds in its environment. This is a major roadblock in human-robot interactions. “While humans have only one pair of ears, a robot can have more! We can place these ‘ears’ anywhere we want — including on its arms!” says Sreenivas.
Effective communication The main points to be considered while looking into human robot interaction techniques are voice and keyword recognition, and gross localisation of sound. The setup required to effectively capture the data needed involves the use of multiple microphones. These are used to capture the data from the surrounding environment after which it is processed in a suitable form to give the required response to the robot.
Through their research, these scientists have developed several techniques which work to make HUBOT communication more effective. One of these techniques is the Y-Array technique. This works in an indoor environment for the localisation and tracking of a moving source. Simply put, this means that even if the robot and master are both in motion, the robot will still be able to efficiently track the commands given. Another technique involves the use of multiple rotating microphones on the robot. This produces the same effect as moving your head around to pick up the location of a sound. 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. First, the robot needs to analyse a real life situation or a physical problem faced by it. It then converts this problem into a mathematical form and written as an algorithm.
The algorithm, a set of simple steps, is then converted into a computer program thus making the robot work accordingly. The microcontrollers in the robot are used to process the required computations. If there are larger computations needed, an external server will be connected to the robot through Wi-Fi to perform them. This avoids unnecessary waiting time and results in the robot’s efficient functioning.
Countering the challenges The team is currently working on several challenges that must be addressed before the ‘HUBOT’ form of communication can be considered perfect. When the source of the sound (master) moves with respect to the robot, the robot cannot follow the commands effectively. Acoustic scene analysis, a technique to process and interpret sound from different perspectives in an environment, is used to solve this. The sound that reaches the many microphones on the robot is detected, classified, localised and identified to help robots ‘hear’ better.
The main goals which the SAG group are intent on achieving include finding newer economical ways to carry out HUBOT communication and to develop new signal processing techniques which can further aid this process. “Although we may not achieve a perfect conversation-type interaction with a robot, we can improve on making the robot follow voice commands more efficiently,” says Sreenivas. Isn’t it exciting to have a HUBOT that listens to you and works for you?
(The author is with Gubbi Labs, a Bengaluru-based research collective)