Acquisition and analysis of robotic data using machine learning techniques
Shivendra Mishra, Radhakrishnan Gopalapillai, Deepa Gupta, T. S. B. Sudarshan · Computational Intelligence and Data Mining · 2015
A robotic system has to understand its environment in order to perform the tasks assigned to it successfully. In such a case, a system capable of learning and decision making is necessary. In order to achieve this capability, a system must be able to observe its environment with the help of real time data received from its sensors. This paper discusses certain experiments to highlight methods and attributes that can be used for such a learning. These experiments consider attributes recorded in different virtual environments with the help of different sensors. Data recording is performed from multiple directions with multiple trials for obtaining different views of the environment. Clustering performed on these multimodal data results in clustering accuracies in the range of 84.3–100 %.