![]() ![]() To demonstrate the improved accuracy of velocity estimates and the more robust State-of-the-art particle-based algorithm on a large publicly available dataset In our evaluations, we compare our approach with a In neural network architectures with recurrent layers working on different In order to apply our approach with measurements from a movingĮgo-vehicle, we propose a method for ego-motion compensation that is applicable ![]() Temporal information for the robust detection of static and dynamicĮnvironment. Due to the combination ofĬonvolutional and recurrent layers, our approach is capable to use spatial and Lidar measurements of a single time step. Our network is fed with sequences of measurement grid maps, which encode the Occupancy grid map, which divides the vehicle surrounding in cells, eachĬontaining the occupancy probability and a velocity estimate. Therefore, we propose to use a recurrent neural network to predict a dynamic Scenarios the motion of other road participants is of special interest. In addition to the detection of objects, in complex traffic Download a PDF of the paper titled Dynamic Occupancy Grid Mapping with Recurrent Neural Networks, by Marcel Schreiber and 2 other authors Download PDF Abstract: Modeling and understanding the environment is an essential task forĪutonomous driving. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |