Model Basis

Created on August 22|Last edited on August 22
Comment
﻿
The prediction model implemented in L5kit is using raster image + CNN, it is similar to the method proposed in the paper "Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks": https://arxiv.org/pdf/1809.10732.pdf and "Multipath": https://arxiv.org/pdf/1910.05449.pdf﻿
💡
Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networks﻿https://medium.com/swlh/review-multimodal-trajectory-predictions-for-autonomous-driving-using-deep-convolutional-networks-596edf8bc102﻿
💡
MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Predictionath﻿https://medium.com/nerd-for-tech/multipath-multiple-probabilistic-anchor-trajectory-hypotheses-for-behavior-prediction-3f687cf00ce0﻿
💡
﻿
Add a comment