Towards Safe Autonomous Driving: Capture Uncertainty in the Deep Neural Network For Lidar 3D Vehicle Detection
This work addresses safety concerns in autonomous driving by improving uncertainty estimation, though it is incremental as it builds on existing detection methods.
The paper tackled the problem of modeling uncertainty in deep neural networks for 3D vehicle detection in Lidar point clouds to enhance autonomous driving safety, resulting in a 1%-5% improvement in detection performance by capturing aleatoric uncertainty.
To assure that an autonomous car is driving safely on public roads, its object detection module should not only work correctly, but show its prediction confidence as well. Previous object detectors driven by deep learning do not explicitly model uncertainties in the neural network. We tackle with this problem by presenting practical methods to capture uncertainties in a 3D vehicle detector for Lidar point clouds. The proposed probabilistic detector represents reliable epistemic uncertainty and aleatoric uncertainty in classification and localization tasks. Experimental results show that the epistemic uncertainty is related to the detection accuracy, whereas the aleatoric uncertainty is influenced by vehicle distance and occlusion. The results also show that we can improve the detection performance by 1%-5% by modeling the aleatoric uncertainty.