SSAD 2026 Talk: Open Datasets Fall Short, End-to-End AV Needs a Babysitter
abursuc · x · 2026-09-18
At the #ssad2026 workshop, researcher abursuc laid out a pessimistic take on autonomous driving:
- Public datasets are insufficient; scaling is limited under non-diverse data
- Open-loop evaluation does not generalize to real driving
- Novel view synthesis fails to generalize on public datasets
- End-to-end approaches still need a "babysitter" to stay safe
- Cameras alone are not enough given real-road accident risk
The thread argues the current scaling playbook for AVs hits fundamental data and generalization bottlenecks.
More from Research
- SSAD 2026 closing talk: Dirk Hornung on OpenXLA as a ready-to-use end-to-end compiler stack — abursuc · 2026-09-18
- VākQA: A Telugu spoken QA benchmark exposing flaws in LLM-as-judge evaluation — SPL-IIITH · 2026-09-18
- Co-Designing AI With Older Adults Boosts Adoption, Usability, WSU Study Finds — pshrink · 2026-09-18
- Salesforce's DarwinX uses an evolutionary approach to fix self-optimizing agent harnesses — bendee983 · 2026-09-18
- tokenbender: no benchmark can capture frontier models' inhuman blind spots in SWE/MLE — tokenbender · 2026-09-18
- Chaining Yes/No Judgments in jev Yields an Embedding-Like Vector — zsakib_ · 2026-09-18