Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
October 8, 2025International Journal for Research in Applied Science and Engineering Technology

A Theoretical Framework for Hybrid Cognitive-Reinforcement Learning Architecture in Safety-Critical Autonomous Systems

View Full Paper
Ask AI
Bookmark
Share

Authors

RSRavi Shankar

Discussion

Loading...

Member takes

Overview

This framework integrates symbolic reasoning and deep reinforcement learning in safety-critical systems, ensuring safety and adaptability.

Key Points

  • The framework innovatively combines symbolic reasoning with deep reinforcement learning, improving safety in critical applications.
  • It offers formal safety bounds and convergence analysis, establishing a rigorous foundation for trustworthy AI systems.
  • The model provides integration principles for diverse decision-making processes, enabling real-time deployment in autonomous systems.
  • Mathematical foundations for multi-modal decision fusion are derived, addressing limitations in existing approaches.

Cite This Study

Ravi Shankar (2025) studied this question.

synapsesocial.com/papers/68e6d7971ffa7aa7d63d171fhttps://doi.org/10.22214/ijraset.2025.74106
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Risk‐Aware Federated Hierarchical Reinforcement Learning for cooperative CAV Safety in Intelligent Transportation System2026 · 1 citations
  2. 2Humans as Safety Constraints: A Survey of Human-in-the-Loop Reinforcement Learning for Critical Systems2026
  3. 3Multi-Agent Reinforcement Learning with Control-Theoretic Safety Guarantees for Dynamic Network Bridging2024
  4. 4A novel intelligent hybrid reinforcement learning framework for autonomous decision making in complex health cognitive systems2026 · 5 citations
  5. 5Hybrid intelligence systems for reliable automation: advancing knowledge work and autonomous operations with scalable AI architectures2025 · 4 citations