PAD:面向自動駕駛的策略感知數據價值評估
PAD: Policy-Aware Data Valuation for Autonomous Driving
PAD提出一套策略感知數據價值評估框架,按目標駕駛策略衡量每段示範數據的效用。在 DiffusionDrive 上,相較只用真實數據訓練,PAD令 EPDMS 在 NavTest 提升 3.5 點、在 NavHard 提升 5.0 點;按策略篩選數據亦優於只用真實數據或完整數據池訓練。
Published on Nov 19
Authors:
,
,
,
,
,
,
Abstract
End-to-end autonomous driving increasingly depends on scaling training demonstrations, yet data growth does not guarantee proportional gains. However, additional data do not guarantee better policies: a demonstration that benefits one planner may be redundant or harmful to another. Existing curation methods typically infer data value from intrinsic sample properties or training-dependent proxies that do not measure downstream policy utility. To address this, we introduce Policy-Aware Data Valuation (PAD), a framework that assigns each candidate demonstration a utility specific to the target driving policy. PAD combines scene-level calibration feedback with projected policy gradients and a regularized approximation of local training geometry, producing scalable influence-based values for the policy. A controlled group-removal study establishes the directional fidelity of these values, while cross-planner analysis shows that the same candidate pool induces markedly different rankings across planner families. On DiffusionDrive, PAD improves EPDMS over real-only training by 3.5 points on NavTest and 5.0 points on NavHard. Policy-specific curation consistently outperforms real-only and full-pool training across diffusion-, regression-, and flow-matching-based planners while substantially reducing scene-level regressions. These results establish policy-aware data valuation as a basis for replacing indiscriminate data accumulation with targeted policy improvement, enabling more efficient and reliable scaling of autonomous-driving systems.
View arXiv page View PDF Project page GitHub Add to collection
Get this paper in your agent:
hf papers read 2611.25604
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.25604 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2611.25604 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.25604 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co