Active Perception using Light Curtains for Autonomous Driving
Active Perception using Light Curtains for Autonomous Driving
复制标题
DOI：
10.1007/978-3-030-58558-7_44
复制
发表时间：
2020-08
期刊：
影响因子：
--
通讯作者：
Siddharth Ancha;Yaadhav Raaj;Peiyun Hu;S. Narasimhan;David Held
中科院分区：
文献类型：
--
作者：
Siddharth Ancha;Yaadhav Raaj;Peiyun Hu;S. Narasimhan;David Held
大多数现实世界的3D传感器，如激光雷达，对整个环境进行固定扫描，同时与处理传感器数据的识别系统分离。在这项工作中，我们提出了一种使用光幕的3D物体识别方法，光幕是一种资源高效的可控传感器，可以测量环境中用户指定位置的深度。关键是，我们提出利用基于深度学习的三维点云检测器的预测不确定性来指导主动感知。鉴于神经网络的不确定性，我们开发了一种新的优化算法来优化放置光幕以最大限度地覆盖不确定区域。通过将设备的物理约束编码成约束图，利用动态规划对约束图进行优化，实现了高效优化。我们展示了如何训练3D探测器通过顺序放置不确定性引导光幕来检测场景中的物体，以连续提高检测精度。代码链接可以在项目网页上找到。
Most real-world 3D sensors such as LiDARs perform fixed scans of the entire environment, while being decoupled from the recognition system that processes the sensor data. In this work, we propose a method for 3D object recognition using light curtains, a resource-efficientcontrollablesensor that measures depth at user-specified locations in the environment. Crucially, we propose using prediction uncertainty of a deep learning based 3D point cloud detector to guide active perception. Given a neural network’s uncertainty, we develop a novel optimization algorithm to optimally place light curtains to maximize coverage of uncertain regions. Efficient optimization is achieved by encoding the physical constraints of the device into a constraint graph, which is optimized with dynamic programming. We show how a 3D detector can be trained to detect objects in a scene by sequentially placing uncertainty-guided light curtains to successively improve detection accuracy. Links to code can be found on the project webpage.