Simultaneous Localization and Mapping (SLAM) in robotics, is when a robot constructions a set of geometrical features of its environment (mapping) and uses sensing to estimate where it is relative to those features (localization). For example, the robot learns where walls are in a building and then can learn how to navigate between a start and goal without hitting them. SLAM sensors have been lidar (3D laser sensor like on Kinect) or bi/tri-ocular (two or three image cameras). This proposal suggests the use of a monocular sensor which is just a single camera that records images without any 3D data. Using the accelerometer and gyroscope along with the camera in a smartphone, some 3D information can be recovered. By using computer vision techniques, the sets of features are found in a sequence of camera frames. From the accelerometer and gyroscope data these are then fitted to statistical estimates of where these features are in the 3D environment. Then using sensor fusion techniques the data is compiled and then traditional SLAM algorithms are used. This would allow SLAM within lower weight, cost, and power sensors. The Smart SPHERES are a direct application of monocular SLAM that are being used to research robotic autonomy. Robotic navigation autonomy is important because it enables robots to aid astronauts with their numerous tasks around the space station with their highly limited time. Second, the technology extends to exploration probes such as the mars rovers which have too much of a communication time delay to be operated purely by teleoporation.