Perception addresses the challenges associated with understanding the environment in which the robotic system is operating. Environmental understanding is achieved through the creation of models that are truthful representations of the robotic system’s operating environment. Many types of sensors can be used for this world-modeling task, including sonar, laser scanners, and radar (see Section 2.5); however, the primary focus of a mobile intelligent autonomous system (MIAS) within the perception research domain is to acquire and interpret visual data. Navigation uses the knowledge of the perceived environment as well as additional information from other on-board sensors to address the challenges of localizing the system within the environment and controlling the platform actuators to maintain a given trajectory. Mapping an unknown environment while simultaneously localizing within that environment is also part of the navigation challenge. Planning addresses the challenge of integrating the knowledge of the high-level goals with the current system perception and localization to generate appropriate behaviors that will take the system closer to successfully achieving these goals. The objective of planning is to generate behavior options and then decide which behavior will be executed. Finally, learning closes the loop by incorporating the knowledge of previous states, behaviors, and results in order to improve the system’s reasoning capability and increase the probability of choosing the optimal behavior.