Scenario-Driven Evaluation of Autonomous Agents: Integrating Large Language Model for UAV Mission Reliability
The Internet of Drones (IoD) integrates autonomous aerial platforms with security, logistics, agriculture, and disaster relief. Decision-making in IoD suffers in real-time adaptability, platform interoperability, and scalability. Conventional decision frameworks with heuristic algorithms and narrow...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/9/3/213 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850089877625896960 |
|---|---|
| author | Anıl Sezgin |
| author_facet | Anıl Sezgin |
| author_sort | Anıl Sezgin |
| collection | DOAJ |
| description | The Internet of Drones (IoD) integrates autonomous aerial platforms with security, logistics, agriculture, and disaster relief. Decision-making in IoD suffers in real-time adaptability, platform interoperability, and scalability. Conventional decision frameworks with heuristic algorithms and narrow Artificial Intelligence (AI) falter in complex environments. To mitigate these, in this study, an augmented decision model is proposed, combining large language models (LLMs) and retrieval-augmented generation (RAG) for enhancing IoD intelligence. Centralized intelligence is achieved by processing environment factors, mission logs, and telemetry, with real-time adaptability. Efficient retrieval of contextual information through RAG is merged with LLMs for timely, correct decision-making. Contextualized decision-making vastly improves adaptability in uncertain environments for a drone network. With LLMs and RAG, the model introduces a scalable, adaptable IoD operations solution. It enables the development of autonomous aerial platforms in industries, with future work in computational efficiency, ethics, and extending operational environments. In-depth analysis with the collection of drone telemetry logs and operational factors was conducted. Decision accuracy, response time, and contextual relevance were measured to gauge system effectiveness. The model’s performance increased remarkably, with a BLEU of 0.82 and a cosine similarity of 0.87, proving its effectiveness for operational commands. Decision latency averaged 120 milliseconds, proving its suitability for real-time IoD use cases. |
| format | Article |
| id | doaj-art-7e9475b8250d49978ff0f751decabb49 |
| institution | DOAJ |
| issn | 2504-446X |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj-art-7e9475b8250d49978ff0f751decabb492025-08-20T02:42:40ZengMDPI AGDrones2504-446X2025-03-019321310.3390/drones9030213Scenario-Driven Evaluation of Autonomous Agents: Integrating Large Language Model for UAV Mission ReliabilityAnıl Sezgin0Research and Development, Siemens A.S, Istanbul 34870, TurkeyThe Internet of Drones (IoD) integrates autonomous aerial platforms with security, logistics, agriculture, and disaster relief. Decision-making in IoD suffers in real-time adaptability, platform interoperability, and scalability. Conventional decision frameworks with heuristic algorithms and narrow Artificial Intelligence (AI) falter in complex environments. To mitigate these, in this study, an augmented decision model is proposed, combining large language models (LLMs) and retrieval-augmented generation (RAG) for enhancing IoD intelligence. Centralized intelligence is achieved by processing environment factors, mission logs, and telemetry, with real-time adaptability. Efficient retrieval of contextual information through RAG is merged with LLMs for timely, correct decision-making. Contextualized decision-making vastly improves adaptability in uncertain environments for a drone network. With LLMs and RAG, the model introduces a scalable, adaptable IoD operations solution. It enables the development of autonomous aerial platforms in industries, with future work in computational efficiency, ethics, and extending operational environments. In-depth analysis with the collection of drone telemetry logs and operational factors was conducted. Decision accuracy, response time, and contextual relevance were measured to gauge system effectiveness. The model’s performance increased remarkably, with a BLEU of 0.82 and a cosine similarity of 0.87, proving its effectiveness for operational commands. Decision latency averaged 120 milliseconds, proving its suitability for real-time IoD use cases.https://www.mdpi.com/2504-446X/9/3/213Internet of Droneslarge language modelscentralized decision-makingautonomous systemsretrieval-augmented generation |
| spellingShingle | Anıl Sezgin Scenario-Driven Evaluation of Autonomous Agents: Integrating Large Language Model for UAV Mission Reliability Drones Internet of Drones large language models centralized decision-making autonomous systems retrieval-augmented generation |
| title | Scenario-Driven Evaluation of Autonomous Agents: Integrating Large Language Model for UAV Mission Reliability |
| title_full | Scenario-Driven Evaluation of Autonomous Agents: Integrating Large Language Model for UAV Mission Reliability |
| title_fullStr | Scenario-Driven Evaluation of Autonomous Agents: Integrating Large Language Model for UAV Mission Reliability |
| title_full_unstemmed | Scenario-Driven Evaluation of Autonomous Agents: Integrating Large Language Model for UAV Mission Reliability |
| title_short | Scenario-Driven Evaluation of Autonomous Agents: Integrating Large Language Model for UAV Mission Reliability |
| title_sort | scenario driven evaluation of autonomous agents integrating large language model for uav mission reliability |
| topic | Internet of Drones large language models centralized decision-making autonomous systems retrieval-augmented generation |
| url | https://www.mdpi.com/2504-446X/9/3/213 |
| work_keys_str_mv | AT anılsezgin scenariodrivenevaluationofautonomousagentsintegratinglargelanguagemodelforuavmissionreliability |