with research on the technological components of the future 6g wireless communication standard in full swing, the possibilities of an ai-native air interface are also being explored. in collaboration with nvidia, rohde & schwarz takes another step forward and presents an enhancement to its recent hardware-in-the-loop demonstration of a neural receiver, showing the achievable performance gains when using trained ai/ml models compared to traditional signal processing – while also optimizing the transmitter side and for the first time taking hardware impairments into account. instead of relying on well-known, symmetric constellations such as qpsk or qam modulations, the constellation points are determined in an end-to-end learning process, which jointly optimizes the neural receiver and the constellation mapper of the transmitter while taking the faded mobile radio channel and carrier frequency offsets into account.
