用于自动驾驶感知与预测的隐式占据流场
Implicit Occupancy Flow Fields for Perception and Prediction in Self-Driving
AI总结：
提出一种统一的感知与未来预测方法，利用单个神经网络隐式表示随时间变化的占据和流，支持运动规划器在连续时空位置直接查询，并通过全局注意力机制克服感受野限制，在城市和高速公路实验中优于现有最先进方法。
摘要：
自动驾驶车辆（SDV）必须能够感知其周围环境并预测其他交通参与者的未来行为。现有工作要么在执行目标检测后对检测到的目标进行轨迹预测，要么预测整个场景的密集占据和流网格。前者存在安全隐患，因为出于效率原因需要将检测数量保持在较低水平，从而牺牲了目标召回率。后者由于输出网格的高维性而在计算上代价高昂，并且受到全卷积网络固有的有限感受野的影响。此外，这两种方法都使用大量计算资源来预测运动规划器可能永远不会查询的区域或目标。这促使我们提出一种统一的感知与未来预测方法，该方法使用单个神经网络隐式表示随时间变化的占据和流。我们的方法避免了不必要的计算，因为它可以在连续的时空位置上直接被运动规划器查询。此外，我们设计了一种架构，通过添加一种高效且有效的全局注意力机制，克服了以往显式占据预测方法感受野有限的问题。通过在城市和高速公路环境中的大量实验，我们证明了我们的隐式模型优于当前最先进的方法。更多信息请访问项目网站：https://waabi.ai/research/implicito。
英文摘要：
A self-driving vehicle (SDV) must be able to perceive its surroundings and predict the future behavior of other traffic participants. Existing works either perform object detection followed by trajectory forecasting of the detected objects, or predict dense occupancy and flow grids for the whole scene. The former poses a safety concern as the number of detections needs to be kept low for efficiency reasons, sacrificing object recall. The latter is computationally expensive due to the high-dimensionality of the output grid, and suffers from the limited receptive field inherent to fully convolutional networks. Furthermore, both approaches employ many computational resources predicting areas or objects that might never be queried by the motion planner. This motivates our unified approach to perception and future prediction that implicitly represents occupancy and flow over time with a single neural network. Our method avoids unnecessary computation, as it can be directly queried by the motion planner at continuous spatio-temporal locations. Moreover, we design an architecture that overcomes the limited receptive field of previous explicit occupancy prediction methods by adding an efficient yet effective global attention mechanism. Through extensive experiments in both urban and highway settings, we demonstrate that our implicit model outperforms the current state-of-the-art. For more information, visit the project website: https://waabi.ai/research/implicito.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
