In this paper, we draw inspiration from Alberto Elfes' pioneering work in
1989, where he introduced the concept of the occupancy grid as World Models for
robots. We imbue the robot with a spatial-temporal world model, termed
UniWorld, to perceive its surroundings and predict the future behavior of other
participants. UniWorld involves initially predicting 4D geometric occupancy as
the World Models for foundational stage and subsequently fine-tuning on
downstream tasks. UniWorld can estimate missing information concerning the
world state and predict plausible future states of the world. Besides,
UniWorld's pre-training process is label-free, enabling the utilization of
massive amounts of image-LiDAR pairs to build a Foundational Model.The proposed
unified pre-training framework demonstrates promising results in key tasks such
as motion prediction, multi-camera 3D object detection, and surrounding
semantic scene completion. When compared to monocular pre-training methods on
the nuScenes dataset, UniWorld shows a significant improvement of about 1.5% in
IoU for motion prediction, 2.0% in mAP and 2.0% in NDS for multi-camera 3D
object detection, as well as a 3% increase in mIoU for surrounding semantic
scene completion. By adopting our unified pre-training method, a 25% reduction
in 3D training annotation costs can be achieved, offering significant practical
value for the implementation of real-world autonomous driving. Codes are
publicly available at this https URL

该研究论文利用 Alberto Elfes 在 1989 年的先驱性工作中引入了占据栅格的概念，并为机器人赋予了一种空间 - 时间世界模型（UniWorld），从而感知其环境并预测其他参与者的未来行为。UniWorld 能够估计世界状态中缺失的信息，并预测世界的合理未来状态，该统一预训练框架在运动预测、多相机三维物体检测和周围场景语义完成等关键任务中展现了有希望的结果，对于实现真实世界的自动驾驶具有重要实用价值。