HARDWARE AND SOFTWARE ARCHITECTURE FOR AUTOMATED DRIVING SYSTEMS

Computer-implemented methods and related aspects for generating predictive output for an Automated Driving System of a vehicle are disclosed. The computer-implemented method comprises, by one or more processors of a first hardware platform of the vehicle, encoding a first sensor dataset generated by a first cluster of sensors of the vehicle using one or more first encoder layers in order to form an encoded first sensor dataset. The method further comprises, by one or more processors of a second hardware platform of the vehicle, encoding a second sensor dataset generated by a second cluster of sensors of the vehicle using one or more second encoder layers in order to form an encoded second sensor dataset. The first and second hardware platforms are separate hardware platforms and wherein each sensor of the first cluster of sensors is different from the sensors of the second cluster of sensors. The computer implemented method further comprises, by one or more processors of the first hardware platform or by one or more processors of the second hardware platform of the vehicle, fusing at least a portion of the encoded first sensor dataset and at least a portion of the encoded second sensor dataset using one or more sensor fusion layers in order to form a set of fused encoded sensor data features, and generating a predictive output based on the set of fused encoded sensor data features using one or more decoder layers. The one or more first encoder layers, the one or more second encoder layers, the one or more sensor fusion layers, and the one or more decoder layers together form an end-to-end trained neural network.