Tracking an unknown number of targets
given noisy measurements from multiple sensors
is critical to autonomous driving. Rao-
Blackwellized particle ltering is well suited
to this problem. Monte Carlo sampling is
used to determine whether measurements are
valid, and if so, which targets they originate
from. This breaks the problem into single
target tracking sub-problems that are solved
in closed form (e.g. with Kalman ltering).
We compare the performance of a traditional
Kalman lter with that of a recurrent neural
network for single target tracking. We
show that LSTMs outperform Kalman ltering
for single target prediction by 2x. We
also present a unique model for training two
dependent LSTMs to output a Gaussian distribution
for a single target prediction to be
used as input to multi-target tracking. We
evaluate the end to end performance of an
LSTM and a Kalman lter for simultaneous
multiple target tracking. In the end to end
pipeline, LSTMs do not provide a signicant
improvement.
