LIDAR-based driving path generation using fully convolutional neural networks
By Luca Caltagirone, Mauro Bellone, Lennart Svensson, Mattias Wahde. 2017
64 citations recorded by the source corpus.
In this work, a novel learning-based approach has been developed to generate driving paths by integrating LIDAR point clouds, GPS-IMU information, and Google driving directions. The system is based on a fully convolutional neural network that jointly learns to carry out perception and path generation from real-world driving sequences and that is trained using automatically generated training examples. Several combinations of input data were tested in order to assess the performance gain provided by specific information modalities. The fully convolutional neural network trained using all the available sensors together with driving directions achieved the best MaxF score of 88.13% when considering a region of interest of 60 × 60 meters. By considering a smaller region of interest, the agreement between predicted paths and ground-truth increased to 92.60%. The positive results obtained in this work indicate that the proposed system may help fill the gap between low-level scene parsing and behavior-reflex approaches by generating outputs that are close to vehicle control and at the same time human-interpretable.
Subfields: Aerospace Engineering, Automotive Engineering, Computer Vision and Pattern Recognition
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
- Javier Alonso-Mora
- Lennart Svensson
- Daniela Rus
- Kazuya Takeda
- Alexander Carballo
- Yu Wu
- Qingqing Niu
- Ekim Yurtsever
In Automotive Engineering
- Yu Wu
- Qingqing Niu
- Zhangjing Wang
- Jacob Lambert
- Alexander Carballo
- Mauro Bellone
- Ekim Yurtsever
- Lennart Svensson
In Computer Vision and Pattern Recognition
- Yu Wu
- Qingqing Niu
- Zhangjing Wang
- Mauro Bellone
- Ekim Yurtsever
- Mattias Wahde
- Luca Caltagirone
- Lennart Svensson
Citations in the corpus
- A Survey of Autonomous Driving: Common Practices and Emerging Technologies (2019, background): “Deep learning FCN [260], segmentation network [261] high imitation performance, but no hard coded safety measures”
- Planning and Decision-Making for Autonomous Vehicles (2018, background): “(68) generated driving paths by integrating lidar point clouds, GPS– inertial measurement unit (IMU) information, and Google navigation information.”
- Multi-Sensor Fusion in Automated Driving: A Survey (2020, methodology): “Besides, in reference [80], the LiDAR point cloud is fused with the GPS-IMU, and the processed data are studied through the fully convolutional neural network, to generate the safe driving route of the vehicle.”
- LIDAR-Camera Fusion for Road Detection Using Fully Convolutional Neural Networks (2018, methodology): “This type of architecture has been successfully used in previous publications, such as [9] and [20], and it is illustrated in Fig.”
- A Survey of End-to-End Driving: Architectures and Training Methods (2020, background): “It is very common to preprocess these points into binary 3D occupancy grids and input them to CNNs [10], [87], [90].”