analiza aiqbench
CADET addresses the critical issue of spurious correlations in end-to-end autonomous driving models by introducing a training-free framework for causal auditing and deconfounding. This approach allows developers to verify whether planners rely on causally irrelevant scene elements without requiring costly retraining or parameter updates, directly enhancing model reliability in long-tail scenarios.
CADET: Physics-Grounded Causal Auditing and Training-Free Deconfounding of End-to-End Driving Planners
arXiv:2606.14438v1 Announce Type: new Abstract: End-to-end (E2E) autonomous-driving planners trained by imitation are prone to statistical shortcuts: they associate scene elements that merely co-occur with expert actions (a roadside object, a building facade) with driving decisions, rather than the variables that causally determine them. Such causal confusion silently compromises reliability in long-tail scenarios, and it is difficult to detect, because prevailing open-loop metrics (L2 displacement and collision rate) are dominated by ego status and do not indicate whether a planner depends on spurious cues. Existing remedies based on causal-intervention training require retraining large models and cannot audit a planner that is already deployed. We present CADET, a training-free framework that audits, benchmarks, and repairs spurious reliance in pretrained E2E planners without any parameter update.
Abstract:End-to-end (E2E) autonomous-driving planners trained by imitation are prone to statistical shortcuts: they associate scene elements that merely co-occur with expert actions (a roadside object, a building facade) with driving decisions, rather than the variables that causally determine them. Such causal confusion silently compromises reliability in long-tail scenarios, and it is difficult to detect, because prevailing open-loop metrics (L2 displacement and collision rate) are dominated by ego status and do not indicate whether a planner depends on spurious cues. Existing remedies based on causal-intervention training require retraining large models and cannot audit a planner that is already deployed. We present CADET, a training-free framework that audits, benchmarks, and repairs spurious reliance in pretrained E2E planners without any parameter update.
Robotics (cs.RO); Artificial Intelligence (cs.AI)
arXiv:2606.14438 [cs.RO]
(or arXiv:2606.14438v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.14438 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 215 cuvinte
Subiecte conexe
CADET: Physics-Grounded Causal Auditing and Training-Free Deconfounding of End-to-End Driving Planners
arXiv · 17 iun. 2026
CADET: Physics-Grounded Causal Auditing and Training-Free Deconfounding of End-to-End Driving Planners
arXiv · 5 aug. 2026
[AINews] not much happened today
Latent Space · 18 sept. 2026
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · 17 sept. 2026