We present an approach to fuse radar and time-of-flight (ToF) range sensor data into an occupancy grid. Fusing the low-level data at sensor level prevents the loss of precious information during compression and pre-processing. Constructing the low-level occupancy grid from raw sensor data enables the detection of occupied cells which are not clearly visible by any of the single sensors. Fusion of the heterogeneous sensor data enhances the perception quality since single sensors fail in certain conditions. Thus, the fusion at low-level holds a high potential to enhance the perception quality for automotive/robotic applications. We demonstrate our approach with real-world data from a mobile sensor platform with three ToF cameras and a 77 GHz high-resolution radar sensor. An occupancy grid is created whenever synchronized sensor data from all sensors is available. The proposed method performed successful detection of multiple pedestrians in different test scenarios. Our approach to build an occupancy grid from radar and optical range sensors can be used as a base in various short-range perception applications (e.g., in robotics or mobile devices).