Technical Report for Argoverse Challenges on 4D Occupancy Forecasting
This work addresses occupancy forecasting for autonomous vehicles, but it is incremental as it builds on existing methods for a specific competition.
The paper tackled 4D occupancy forecasting for autonomous driving by proposing a LiDAR-based BEV encoder with temporal fusion and a two-stage decoder, achieving an 18% lower L1 error (3.57) than the baseline and first place in the Argoverse Challenges.
This report presents our Le3DE2E_Occ solution for 4D Occupancy Forecasting in Argoverse Challenges at CVPR 2023 Workshop on Autonomous Driving (WAD). Our solution consists of a strong LiDAR-based Bird's Eye View (BEV) encoder with temporal fusion and a two-stage decoder, which combines a DETR head and a UNet decoder. The solution was tested on the Argoverse 2 sensor dataset to evaluate the occupancy state 3 seconds in the future. Our solution achieved 18% lower L1 Error (3.57) than the baseline and got the 1 place on the 4D Occupancy Forecasting task in Argoverse Challenges at CVPR 2023.