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.

翻译：本报告介绍了我们在CVPR 2023自动驾驶研讨会（WAD）Argoverse挑战赛中提出的Le3DE2E_Occ解决方案，用于4D占用预测任务。该方案包含一个基于激光雷达的强鸟瞰图（BEV）编码器（集成时间融合模块）与双阶段解码器（结合DETR头部和UNet解码器）。我们在Argoverse 2传感器数据集上测试了该方案，用于评估未来3秒的占用状态。相较于基线方法，我们的方案将L1误差降低18%（达到3.57），并在CVPR 2023 Argoverse挑战赛的4D占用预测任务中获得第一名。