mlsanityData to 14 Oct 2026

Hallucination-Aware Generative Pretrained Transformer for Cooperative Aerial Mobility Control

arXiv 2504.10831 ↗First posted 15 Apr 2025cs.AI cs.ROcited by 3

On the map: Deep reinforcement learning methods → RL for robot navigation and UAV control

Abstract (arXiv)

This paper proposes SafeGPT, a two-tiered framework that integrates generative pretrained transformers (GPTs) with reinforcement learning (RL) for efficient and reliable unmanned aerial vehicle (UAV) last-mile deliveries. In the proposed design, a Global GPT module assigns high-level tasks such as sector allocation, while an On-Device GPT manages real-time local route planning. An RL-based safety filter monitors each GPT decision and overrides unsafe actions that could lead to battery depletion or duplicate visits, effectively mitigating hallucinations. Furthermore, a dual replay buffer mechanism helps both the GPT modules and the RL agent refine their strategies over time. Simulation results demonstrate that SafeGPT achieves higher delivery success rates compared to a GPT-only baseline, while substantially reducing battery consumption and travel distance. These findings validate the efficacy of combining GPT-based semantic reasoning with formal safety guarantees, contributing a viable solution for robust and energy-efficient UAV logistics.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods. Builds on 8 of its 11 references that are in the map. First posted on arXiv 15 Apr 2025.

Builds on

8 of 11 references.

References · 8

  1. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  2. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  3. 2017Constrained Policy Optimizationcited by 983
  4. 2023Safe RLHF: Safe Reinforcement Learning from Human Feedbackcited by 656
  5. 2023Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agentscited by 69
  6. 2016Vehicle Routing Problems for Drone Deliverycited by 24
  7. 2025Safety Aware Task Planning via Large Language Models in Roboticscited by 24
  8. 2023Multi-Agent Reinforcement Learning for Cooperative Air Transportation Services in City-Wide Autonomous Urban Air Mobilitycited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025How Can Quantum Deep Learning Improve Large Language Models?cited by 1
  2. 2025Safe and Economical UAV Trajectory Planning in Low-Altitude Airspace: A Hybrid DRL-LLM Approach with Compliance Awarenesscited by 0
  3. 2026A Tutorial on Quantum Amplitude Embedding with Data Re-Uploadingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Recent Advances in Transformer and Large Language Models for UAV Applications
  2. 2025Large Language Model-Empowered Decision Transformer for UAV-Enabled Data Collection
  3. 2026High-Speed Vision-Based Flight in Clutter with Safety-Shielded Reinforcement Learning
  4. 2024Transformer-Based Fault-Tolerant Control for Fixed-Wing UAVs Using Knowledge Distillation and In-Context Adaptation
  5. 2025Decision Transformer-Based Drone Trajectory Planning with Dynamic Safety-Efficiency Trade-Offs
  6. 2025Transformer-Guided Deep Reinforcement Learning for Optimal Takeoff Trajectory Design of an eVTOL Drone
  7. 2026Lightweight Safe Reinforcement Learning for End-to-End UAV Navigation
  8. 2024TRUST-UP: Trustworthy Reinforcement learning Using Safe Techniques for UAV Pursuit