Multi-object positioning using mixture density networks

A system, comprising:

• a memory comprising computer-executable instructions;
• and
• one or more processors configured to execute the computer-executable instructions and cause the system to perform an operation comprising:
• receiving radio frequency (RF) signal data collected in a physical space;
• generating a feature vector encoding the RF signal data by processing the RF signal data using a first neural network;
• processing the feature vector using a first mixture model to generate:
• a first encoding tensor indicating a set of moving objects in the physical space;
• a first location tensor indicating a location of each of the moving objects in the physical space;
• and
• a first uncertainty tensor indicating uncertainty of the locations of each of the moving objects in the physical space;
• and
• outputting at least one location from the first location tensor.

A method, comprising:

• collecting a set of signal data records in a physical space while one or more objects move around the physical space;
• determining, for each signal data record, a ground truth location of each of the one or more objects in the physical space;
• generating a predicted location of each of the one or more objects using a first neural network and a first mixture model;
• computing a loss based on the ground truth locations and the predicted locations;
• and
• refining one or more parameters of the first neural network and the first mixture model based on the loss such that the first neural network and the first mixture model are trained to position multiple objects moving in the physical space.

A system, comprising:

• a memory comprising computer-executable instructions;
• and
• one or more processors configured to execute the computer-executable instructions and cause the system to perform an operation comprising:
• collecting a set of signal data records in a physical space while one or more objects move around the physical space;
• determining, for each signal data record, a ground truth location of each of the one or more objects in the physical space;
• generating a predicted location of each of the one or more objects using a first neural network and a first mixture model;
• computing a loss based on the ground truth locations and the predicted locations;
• and
• refining one or more parameters of the first neural network and the first mixture model based on the loss such that the first neural network and the first mixture model are trained to position multiple objects moving in the physical space.