This study compares the performances of di erent classication schemes and fusion techniques for target di erentiation and localization of commonly encountered features in indoor robot environments using sonar sensing Di erentiation of such features is of interest for intelligent systems in a variety of applications such as system control based on acoustic signal detection and identication map building navigation obstacle avoidance and target tracking The classication schemes employed include the target di erentiation algorithm developed by Ayrulu and Barshan statistical pattern recognition techniques fuzzy c means clustering algorithm and articial neural networks The fusion techniques used are Dempster Shafer evidential reasoning and di erent voting schemes To solve the consistency problem arising in simple ma jority voting di erent voting schemes including preference ordering and reliability measures are proposed and veried experimentally To improve the performance of neural network classiers di erent input signal representations two di erent training algorithms and both modular and non modular network structures are considered The best classication and localization scheme is found to be the neural network classier trained with the wavelet transform of the sonar signals This method is applied to map building in mobile robot environments Physically di erent sensors such as infrared sensors and structured light systems besides sonar sensors are also considered to improve the performance in target classication and localization.