Metraipolis › archive › dc_f071a60ff5fb

Self-Aware Active Learning Enables Continual Improvement in Autonomous Driving — arXiv:2608.29772

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.29772
License (as archived)
CC0-1.0
Archived
2026-10-17T10:06:51.873Z
SHA-256 of the archived text
76510da492fd23ab42778b91e0997cf07cbf0b62db6ba3c0be2e8e94c145f2a2
Stable URL of this page
https://metraipolis.com/documento/dc_f071a60ff5fb

How to cite

Self-Aware Active Learning Enables Continual Improvement in Autonomous Driving — arXiv:2608.29772 — arXiv (en), https://arxiv.org/abs/2608.29772 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f071a60ff5fb (Metraipolis archive dc_f071a60ff5fb, sha256 76510da492fd23ab42778b91e0997cf07cbf0b62db6ba3c0be2e8e94c145f2a2)
BibTeX
@misc{dcf071a60ff5fb,
  title = {Self-Aware Active Learning Enables Continual Improvement in Autonomous Driving — arXiv:2608.29772},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.29772},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f071a60ff5fb; sha256 76510da492fd23ab42778b91e0997cf07cbf0b62db6ba3c0be2e8e94c145f2a2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29772. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Learning-based autonomous driving (AD) systems can perform reliably in familiar conditions, yet rare distribution shifts and long-tail events remain a major source of abrupt failure. A central limitation is that most agents learn primarily from passive experience and lack mechanisms to estimate when their competence is insufficient, seek timely assistance, and convert safety-critical encounters into targeted improvement. Here we present self-aware guided exploration (SAGE), an active learning framework for post-training adaptation in AD. SAGE learns a predictive world model that generates two online intrinsic signals: fear, which estimates short-horizon predictive risk and model uncertainty, and curiosity, which measures novelty through prediction error. Curiosity adaptively calibrates the intervention threshold for fear, allowing the agent to regulate risk in a context-dependent manner. When predicted fear exceeds this adaptive threshold, the agent transfers control to an expert or fallback policy and uses the resulting takeover trajectories for focused imitation learning. In parallel, fear is integrated into policy optimization and evaluation as a safety-oriented constraint to reduce performance regressions during adaptation. We evaluate SAGE in simulated route-transfer tasks, Waymo-based logged driving scenarios, CARLA occlusion hazards, and real-world mobile robot navigation tests. Across these settings, SAGE improves robustness in novel and safety-critical scenarios, reduces safety violations, and maintains task performance comparable to strong baseline policies. These results suggest that agents can improve after initial training by estimating the limits of their competence, requesting guidance when needed, and learning selectively from rare high-value events.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.29772 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T09:58:57.794Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).