With the advancements of robotic technologies, the medical environments are adopting more and more as pects of automation to enhance the services in hos pitals. In pandemic conditions such as COVID 19, direct contact with patients may result in the s preadi ng of disease. Hence the health community finds difficulty in distri buting medicines and disposal of waste. The design and development of an automatic gui ded vehicle for hos pital applicati ons, which can be controlled remotely is specified here. AGV is a line follower robot, powered by a battery that can be charged from solar energy. It has infrared sensors at the bottom for path i dentification and an ultrasonic sensor hel d i n front of the vehicle for obstacle detection. It collects medicines from the nurse's station and follows the path provi ded to reach the suppl y point, which is the patient's bed. The sensors provi ded will detect the bed and opens the correspondi ng box of medicine. In addi tion to this, it hel ps i n real-time monitoring of patient's parameters such as temperature, pulse rate, etc. and sends informati on to the doctor through the internet. AGV also collects waste from the bi n and dump it to a proper place.

No abstract

Due to the increased customer demand for various applications in various fields, service robots are becoming very popular. Human Robot Interaction (HRI) is very essential for the good performance of the home service robot. A robot can be controlled by many methods and here the robot is controlled by voice commands which are given orally. The robot must be able to perform various tasks such as speech source localization, source separation and classification etc. The robot must be capable to identify the source accurately. The speech recognizer and a speaker classifier are used to improve the performance of the robot. Reverberation deteriorates the quality and intelligibility of speech. This leads to the poor performance of classification systems. The noise effects can also degrade the performance of the classification systems. The channel may also have ISI. So channel must be equalized to nullify these effects. Here a new blind deconvolutive neural network is used for speech classification in the robot. Using this new method the robot can identify the commands given to it more accurately than by the existing methods.

No abstract

No abstract