Abstract-Outdoor mobile applications are becoming popular in fields such as gaming, tourism and environment monitoring. They rely on the input of multiple, possibly noisy, sensors, such as the camera, GPS, compass and gyroscope. The regression testing of such applications requires the reproduction of the real conditions in which the application works, which are hard to reproduce without automated support. We present a capture & replay framework that automates regression testing of mobile outdoor applications, by recording data streams in real-time on the field from multiple sensors, replays them in lab and computes quality metrics to trace regression errors.