Guardado en:
Detalles Bibliográficos
Autores principales: Bi, Jing, Wen, Lianggong Bruce, Liu, Zhang, Xu, Chenliang
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2506.21250
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909660657745920
author Bi, Jing
Wen, Lianggong Bruce
Liu, Zhang
Xu, Chenliang
author_facet Bi, Jing
Wen, Lianggong Bruce
Liu, Zhang
Xu, Chenliang
contents This paper introduces ACTLLM (Action Consistency Tuned Large Language Model), a novel approach for robot manipulation in dynamic environments. Traditional vision-based systems often struggle to learn visual representations that excel in both task execution and spatial reasoning, thereby limiting their adaptability in dynamic environments. ACTLLM addresses these challenges by harnessing language to craft structured scene descriptors, providing a uniform interface for both spatial understanding and task performance through flexible language instructions. Moreover, we introduce a novel action consistency constraint that aligns visual perception with corresponding actions, thereby enhancing the learning of actionable visual representations. Additionally, we have reformulated the Markov decision process for manipulation tasks into a multi-turn visual dialogue framework. This approach enables the modeling of long-term task execution with enhanced contextual relevance derived from the history of task execution. During our evaluation, ACTLLM excels in diverse scenarios, proving its effectiveness on challenging vision-based robot manipulation tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21250
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ACTLLM: Action Consistency Tuned Large Language Model
Bi, Jing
Wen, Lianggong Bruce
Liu, Zhang
Xu, Chenliang
Robotics
This paper introduces ACTLLM (Action Consistency Tuned Large Language Model), a novel approach for robot manipulation in dynamic environments. Traditional vision-based systems often struggle to learn visual representations that excel in both task execution and spatial reasoning, thereby limiting their adaptability in dynamic environments. ACTLLM addresses these challenges by harnessing language to craft structured scene descriptors, providing a uniform interface for both spatial understanding and task performance through flexible language instructions. Moreover, we introduce a novel action consistency constraint that aligns visual perception with corresponding actions, thereby enhancing the learning of actionable visual representations. Additionally, we have reformulated the Markov decision process for manipulation tasks into a multi-turn visual dialogue framework. This approach enables the modeling of long-term task execution with enhanced contextual relevance derived from the history of task execution. During our evaluation, ACTLLM excels in diverse scenarios, proving its effectiveness on challenging vision-based robot manipulation tasks.
title ACTLLM: Action Consistency Tuned Large Language Model
topic Robotics
url https://arxiv.org/abs/2506.21250