Deep Object Tracking on Dynamic Occupancy Grid Maps Using RNNs

Multi-Step Prediction of Occupancy Grid Maps With Recurrent Neural Networks

“…Authors in [10] and [4] employ Dynamic OGMs (DOGMa). DOGMa is the result of fusing a variety of sensor readings using Bayesian filtering, which associates dynamic information to each cell as well as the occupancy state [18].…”

“…The dynamic information contains the velocity and its uncertainty. An encoder-decoder structure with Convolutional Long-Short-Term-Memory network (Con-vLSTM) [27] receives DOGMa and produces the occupancy probability of static regions alongside the anchor boxes for dynamic objects [4]. An automatic output label generation is also used which can have a "relatively high false negative rate" [10].…”

“…An automatic output label generation is also used which can have a "relatively high false negative rate" [10]. Additionally, the datasets in [10] and [4] are collected from a static sensor (parked car).…”

“…Alternatively, it is possible to provide multi-steps of OGM prediction into the future [2,4,10]. Multi-step prediction of OGMs in a dynamic environment provides the drivable space for a planning algorithm without the need for the several stages required in the classic approach.…”

“…Recurrent Neural Networks (RNNs) are, therefore, a potential model candidate, which have also been successfully applied to various other problems with dynamic nature, such as unsupervised video prediction [12,7], multi-step prediction of mobile robots [15] and visual odometry [25]. Moreover, it is shown that RNNs can produce promising results in the context of OGM prediction [2,4].…”