LAMARS: Large Language Model-Based Anticipation Mechanism Acceleration in Real-Time Robotic Systems
Large language models (LLMs) have assumed an increasingly crucial role in robotic systems because of their ability to leverage the extensive knowledge they possess in robotic inference and task handling. Although LLMs offer significant potential, their integration into robotic systems poses substant...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10819383/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533390658994176 |
|---|---|
| author | Yifang Gao Wei Luo Xuye Wang Shunshun Zhang Patrick Goh |
| author_facet | Yifang Gao Wei Luo Xuye Wang Shunshun Zhang Patrick Goh |
| author_sort | Yifang Gao |
| collection | DOAJ |
| description | Large language models (LLMs) have assumed an increasingly crucial role in robotic systems because of their ability to leverage the extensive knowledge they possess in robotic inference and task handling. Although LLMs offer significant potential, their integration into robotic systems poses substantial challenges, particularly with regard to computational efficiency and latency. To address this challenge, this study presents LAMARS, an LLM-based anticipation mechanism designed to accelerate real-time robotic systems. LAMARS leverages the predictive power and zero-shot capabilities of LLMs combined with an anticipation mechanism and vision-language processing to position a robot in advance for upcoming tasks. This reduces latency and optimizes path planning without requiring expensive training data. Our evaluations in a realistic simulation environment and with a variation of the RLBench dataset demonstrated that LAMARS achieved an average success rate of 0.79 and improves efficiency by up to 52.4% compared to existing methods, significantly lowering path planning costs. These results indicate that LAMARS effectively accelerates directive execution, making it a promising solution to minimize delays in real-time robotic systems. |
| format | Article |
| id | doaj-art-2255bc3321a540759c9a52eb36203d8a |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-2255bc3321a540759c9a52eb36203d8a2025-01-16T00:01:24ZengIEEEIEEE Access2169-35362025-01-01133864388010.1109/ACCESS.2024.352490610819383LAMARS: Large Language Model-Based Anticipation Mechanism Acceleration in Real-Time Robotic SystemsYifang Gao0https://orcid.org/0000-0003-2858-5285Wei Luo1Xuye Wang2Shunshun Zhang3Patrick Goh4https://orcid.org/0000-0002-4514-5065School of Electrical and Electronic Engineering, Universiti Sains Malaysia, Nibong Tebal, Penang, MalaysiaSchool of Electrical Engineering, Beijing Jiaotong University, Beijing, ChinaSchool of Pharmaceutical Sciences, Universiti Sains Malaysia, Gelugor, Penang, MalaysiaSchool of Automation, Guangxi University of Science and Technology, Liuzhou, ChinaSchool of Electrical and Electronic Engineering, Universiti Sains Malaysia, Nibong Tebal, Penang, MalaysiaLarge language models (LLMs) have assumed an increasingly crucial role in robotic systems because of their ability to leverage the extensive knowledge they possess in robotic inference and task handling. Although LLMs offer significant potential, their integration into robotic systems poses substantial challenges, particularly with regard to computational efficiency and latency. To address this challenge, this study presents LAMARS, an LLM-based anticipation mechanism designed to accelerate real-time robotic systems. LAMARS leverages the predictive power and zero-shot capabilities of LLMs combined with an anticipation mechanism and vision-language processing to position a robot in advance for upcoming tasks. This reduces latency and optimizes path planning without requiring expensive training data. Our evaluations in a realistic simulation environment and with a variation of the RLBench dataset demonstrated that LAMARS achieved an average success rate of 0.79 and improves efficiency by up to 52.4% compared to existing methods, significantly lowering path planning costs. These results indicate that LAMARS effectively accelerates directive execution, making it a promising solution to minimize delays in real-time robotic systems.https://ieeexplore.ieee.org/document/10819383/Human-robot interactionlarge language modelslatency reductionvision-language modelspath planning |
| spellingShingle | Yifang Gao Wei Luo Xuye Wang Shunshun Zhang Patrick Goh LAMARS: Large Language Model-Based Anticipation Mechanism Acceleration in Real-Time Robotic Systems IEEE Access Human-robot interaction large language models latency reduction vision-language models path planning |
| title | LAMARS: Large Language Model-Based Anticipation Mechanism Acceleration in Real-Time Robotic Systems |
| title_full | LAMARS: Large Language Model-Based Anticipation Mechanism Acceleration in Real-Time Robotic Systems |
| title_fullStr | LAMARS: Large Language Model-Based Anticipation Mechanism Acceleration in Real-Time Robotic Systems |
| title_full_unstemmed | LAMARS: Large Language Model-Based Anticipation Mechanism Acceleration in Real-Time Robotic Systems |
| title_short | LAMARS: Large Language Model-Based Anticipation Mechanism Acceleration in Real-Time Robotic Systems |
| title_sort | lamars large language model based anticipation mechanism acceleration in real time robotic systems |
| topic | Human-robot interaction large language models latency reduction vision-language models path planning |
| url | https://ieeexplore.ieee.org/document/10819383/ |
| work_keys_str_mv | AT yifanggao lamarslargelanguagemodelbasedanticipationmechanismaccelerationinrealtimeroboticsystems AT weiluo lamarslargelanguagemodelbasedanticipationmechanismaccelerationinrealtimeroboticsystems AT xuyewang lamarslargelanguagemodelbasedanticipationmechanismaccelerationinrealtimeroboticsystems AT shunshunzhang lamarslargelanguagemodelbasedanticipationmechanismaccelerationinrealtimeroboticsystems AT patrickgoh lamarslargelanguagemodelbasedanticipationmechanismaccelerationinrealtimeroboticsystems |