Apple Inc. (AAPL) is tossing its hat into the autonomous driving ring.
Research by Apple computer scientists on the way self-driving cars can better spot pedestrians and cyclists with fewer sensors was posted online in what appears to be the company's first publicly available paper on autonomous vehicles operations.
The paper, which was submitted to independent online journal arXiv by Apple scientists Yin Zhou and Oncel Tuzel, proposes a new software approach to autonomous driving called VoxelNet. The VoxelNet approach helps computers detect three-dimensional objects with more accuracy and fewer sensors.
The paper is titled "VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection." The research abstract includes the following: "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."
It's an uncommon move for Apple to disclose the VoxelNet research, as the company has historically played its future products cards very close to the vest.
Apple shares were higher in early trading Wednesday.
More of What's Trending on TheStreet: