Apple has posted research on how self-driving cars can better spot objects while using fewer sensors. It appears to be the company’s first publicly disclosed paper on autonomous vehicles.
The approach called “VoxelNet” is significant because Apple’s corporate secrecy around future products has been seen as a drawback among AI and machine learning researchers. Here’s the summary of Apple’s research paper:
Accurate detection of objects in 3D point clouds is a central problem in many applications, such as autonomous navigation, housekeeping robots, and augmented/virtual reality. To interface a highly sparse LiDAR point cloud with a region proposal network (RPN), most existing efforts have focused on hand-crafted feature representations, for example, a bird’s eye view projection. In this work, we remove the need of manual feature engineering for 3D point clouds and propose VoxelNet, a generic 3D detection network that unifies feature extraction and bounding box prediction into a single stage, end-to-end trainable deep network. Specifically, VoxelNet divides a point cloud into equally spaced 3D voxels and transforms a group of points within each voxel into a unified feature representation through the newly introduced voxel feature encoding (VFE) layer. In this way, the point cloud is encoded as a descriptive volumetric representation, which is then connected to a RPN to generate detections. Experiments on the KITTI car detection benchmark show that VoxelNet outperforms the state-of-the-art LiDAR based 3D detection methods by a large margin. Furthermore, our network learns an effective discriminative representation of objects with various geometries, leading to encouraging results in 3D detection of pedestrians and cyclists, based on only LiDAR.
Though Apple CEO Tim Cook has called self-driving cars “the mother of all AI projects,” Apple has given few hints about the nature of its self-driving car ambitious. In April, Apple filed a self-driving car testing plan with California regulators.
