Capturing Object Detection Uncertainty in Multi-Layer Grid Maps
This addresses uncertainty estimation for safer trajectory planning in automated driving, but it is incremental as it builds on existing object detection methods.
The paper tackles the problem of object detection uncertainty in automated driving by proposing a deep convolutional detector that estimates classification, pose, and shape uncertainty, trained on the KITTI dataset, with some models showing similar performance and superior robustness compared to prior detectors.
We propose a deep convolutional object detector for automated driving applications that also estimates classification, pose and shape uncertainty of each detected object. The input consists of a multi-layer grid map which is well-suited for sensor fusion, free-space estimation and machine learning. Based on the estimated pose and shape uncertainty we approximate object hulls with bounded collision probability which we find helpful for subsequent trajectory planning tasks. We train our models based on the KITTI object detection data set. In a quantitative and qualitative evaluation some models show a similar performance and superior robustness compared to previously developed object detectors. However, our evaluation also points to undesired data set properties which should be addressed when training data-driven models or creating new data sets.