Timezone: »
Benchmark datasets for autonomous driving, such as KITTI, nuScenes, Argoverse, or Waymo are realistic but designed to be faultless. These datasets do not contain errors, difficult driving maneuvers, or other corner cases. We propose a framework for perturbing autonomous vehicle datasets, the DANGER framework, which generates edge-case images on top of current autonomous driving datasets. The input to DANGER are photorealistic datasets from real driving scenarios. We present the DANGER algorithm for vehicle position manipulation and the interface towards the renderer module, and present five scenario-level dangerous primitives generation applied to the virtual KITTI and virtual KITTI 2 datasets. Our experiments prove that DANGER can be used as a framework for expanding the current datasets to cover generative while realistic and anomalous corner cases.
Author Information
Shengjie Xu (University of California, Santa Cruz)
Lan Mi
Leilani Gilpin (UC Santa Cruz)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 : A Framework for Generating Dangerous Scenes for Testing Robustness »
Fri. Dec 2nd 08:47 -- 08:53 PM Room
More from the Same Authors
-
2023 Poster: Towards a fuller understanding of neurons with Clustered Compositional Explanations »
Biagio La Rosa · Leilani Gilpin · Roberto Capobianco -
2022 Workshop: Progress and Challenges in Building Trustworthy Embodied AI »
Chen Tang · Karen Leung · Leilani Gilpin · Jiachen Li · Changliu Liu -
2021 : Q/A Session »
Leilani Gilpin · Julius Adebayo -
2021 : Speaker Introduction »
Leilani Gilpin -
2021 : Q/A Session »
Leilani Gilpin -
2021 : Speaker Introduction »
Leilani Gilpin -
2021 Workshop: eXplainable AI approaches for debugging and diagnosis »
Roberto Capobianco · Biagio La Rosa · Leilani Gilpin · Wen Sun · Alice Xiang · Alexander Feldman -
2018 : Posters 1 »
Wei Wei · Flavio Calmon · Travis Dick · Leilani Gilpin · Maroussia Lévesque · Malek Ben Salem · Michael Wang · Jack Fitzsimons · Dimitri Semenovich · Linda Gu · Nathaniel Fruchter