"Let's kick things off with a video. As you watch it, I want you to think about how you might go about describing what's happening in the scene, and how maybe you could implement something to find scenes similar to it in a large corpus. Maybe you're thinking you could use object detection methods to work out there's something in the road."
"It's a good approach, but what about this scene? How would you describe it? This scenario is what we would call an edge case. It's a rare, unexpected, or unusual scenario that falls outside our typical operating conditions. Most driving scenarios encountered by autonomous vehicles involve routine tasks such as lane following, maintaining safe following distances, and navigating predictable road conditions."
Edge cases are rare, unexpected, or unusual driving scenarios that fall outside typical operating conditions and are underrepresented in driving datasets. Common driving situations like lane following and maintaining safe distances dominate datasets, which makes finding unusual scenarios difficult. These rare events pose significant safety risks for autonomous vehicles and therefore require explicit identification and retrieval. Locating edge cases is analogous to searching for a needle among many haystacks. Prioritizing discovery and inclusion of edge cases improves training data diversity and enables more rigorous evaluation of model robustness and real-world safety.
Read at InfoQ
Unable to calculate read time
Collection
[
|
...
]