Metraipolis › archive › dc_b7614ba2e182

Towards Trustworthy Autonomous Robots: An Explainable AI-Based Decision Framework — arXiv:2609.02861

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02861
License (as archived)
CC0-1.0
Archived
2026-10-17T03:38:42.175Z
SHA-256 of the archived text
2b41f42bc49c20982a4e463aee201c15a42864837de046c442a2c4c879765922
Stable URL of this page
https://metraipolis.com/documento/dc_b7614ba2e182

How to cite

Towards Trustworthy Autonomous Robots: An Explainable AI-Based Decision Framework — arXiv:2609.02861 — arXiv (en), https://arxiv.org/abs/2609.02861 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b7614ba2e182 (Metraipolis archive dc_b7614ba2e182, sha256 2b41f42bc49c20982a4e463aee201c15a42864837de046c442a2c4c879765922)
BibTeX
@misc{dcb7614ba2e182,
  title = {Towards Trustworthy Autonomous Robots: An Explainable AI-Based Decision Framework — arXiv:2609.02861},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02861},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b7614ba2e182; sha256 2b41f42bc49c20982a4e463aee201c15a42864837de046c442a2c4c879765922},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02861. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autonomous robots powered by deep learning face a fundamental auditability challenge: when incidents occur, investigators cannot reconstruct why the system made specific decisions. This paper presents TRACE (Transparent Reasoning Architecture for Credible Execution), a decision framework that ensures every autonomous action can be traced back to sensor evidence through documented causal chains. The framework organizes decision-making into four auditable layers: Semantic Perception for evidence-grounded entity recognition, Belief Reasoning for probabilistic state estimation with causal graphs, Action Synthesis for constraint-aware planning with counterfactual documentation, and Execution Verification for compliance monitoring. TRACE is model-agnostic yet designed to integrate learning-based perception modules (CNNs, transformers) while preserving decision-level auditability. We evaluate the framework using three objective metrics: Evidence Traceability (sensor-to-decision linkage), Decision Reconstructability (post-hoc analysis capability), and Temporal Continuity (audit trail completeness). Experimental evaluation on warehouse robot navigation demonstrates that TRACE achieves 98.6% evidence traceability, 99.0% temporal continuity, and 98.1% decision reconstructability across 500 simulated decision cycles. Post-hoc methods like LIME provide feature attributions but lack the artifact structure needed for decision-level reconstruction. The framework addresses EU AI Act requirements for high-risk system transparency and contributes to Explainable AI for safety-critical autonomous systems.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.02861 — 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 2026-10-17T03:13:12.574Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).