L3-Net: Towards Learning Based LiDAR Localization for Autonomous Driving

By Weixin Lu, Yao Zhou, Guowei Wan, Shenhua Hou, Shiyu Song. Computer Vision and Pattern Recognition, 2019

304 citations recorded by the source corpus.

We present L3-Net - a novel learning-based LiDAR localization system that achieves centimeter-level localization accuracy, comparable to prior state-of-the-art systems with hand-crafted pipelines. Rather than relying on these hand-crafted modules, we innovatively implement the use of various deep neural network structures to establish a learning-based approach. L3-Net learns local descriptors specifically optimized for matching in different real-world driving scenarios. 3D convolutions over a cost volume built in the solution space significantly boosts the localization accuracy. RNNs are demonstrated to be effective in modeling the vehicle's dynamics, yielding better temporal smoothness and accuracy. We comprehensively validate the effectiveness of our approach using freshly collected datasets. Multiple trials of repetitive data collection over the same road and areas make our dataset ideal for testing localization systems. The SunnyvaleBigLoop sequences, with a year's time interval between the collected mapping and testing data, made it quite challenging, but the low localization error of our method in these datasets demonstrates its maturity for real industrial implementation.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/0df81be86926562d02048755e11ca7a6582aa6c5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Pengfei Yuan
2. Yao Zhou
3. Shiyu Song
4. Guowei Wan
5. Weixin Lu

In Computer Vision and Pattern Recognition

1. L. Jiao
2. Rong Qu
3. Pengfei Yuan
4. Shuyuan Yang
5. Zhixi Feng
6. Yao Zhou
7. Shiyu Song
8. Fang Liu

Citations in the corpus

• A Survey of Deep Learning-Based Object Detection (2019, methodology): “[171] utilize a novel architecture contains 3D convolutions and RNNs to achieve”
• DeepVCP: An End-to-End Deep Neural Network for Point Cloud Registration (2019, methodology): “Another dataset that is used for evaluation is the ApolloSouthBay dataset [25].”