Sensor Fusion for Autonomous Outdoor Navigation Using Neural Networks

Abstract

For many navigation tasks, a single sensing modality is sufficiently rich to accomplish the desired motion control goals; for practical autonomous outdoor navigation, a single sensing modality is a crippling limitation on what tasks can be undertaken. In the research detailed in this paper, we open the door for a whole new suite of real-time autonomous navigation tasks previously unattainable. Using neural networks, including a neural network paradigm particularly well suited to sensor fusion, and Carnegie Mellon University's HMMWV off-road vehicle, we have successfully performed simulated and real-world navigation tasks that required the use of multiple sensing modalities.