Salvato in:
Dettagli Bibliografici
Autori principali: Zheng, Ruijie, Liang, Yongyuan, Huang, Shuaiyi, Gao, Jianfeng, Daumé III, Hal, Kolobov, Andrey, Huang, Furong, Yang, Jianwei
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2412.10345
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908395716476928
author Zheng, Ruijie
Liang, Yongyuan
Huang, Shuaiyi
Gao, Jianfeng
Daumé III, Hal
Kolobov, Andrey
Huang, Furong
Yang, Jianwei
author_facet Zheng, Ruijie
Liang, Yongyuan
Huang, Shuaiyi
Gao, Jianfeng
Daumé III, Hal
Kolobov, Andrey
Huang, Furong
Yang, Jianwei
contents Although large vision-language-action (VLA) models pretrained on extensive robot datasets offer promising generalist policies for robotic learning, they still struggle with spatial-temporal dynamics in interactive robotics, making them less effective in handling complex tasks, such as manipulation. In this work, we introduce visual trace prompting, a simple yet effective approach to facilitate VLA models' spatial-temporal awareness for action prediction by encoding state-action trajectories visually. We develop a new TraceVLA model by finetuning OpenVLA on our own collected dataset of 150K robot manipulation trajectories using visual trace prompting. Evaluations of TraceVLA across 137 configurations in SimplerEnv and 4 tasks on a physical WidowX robot demonstrate state-of-the-art performance, outperforming OpenVLA by 10% on SimplerEnv and 3.5x on real-robot tasks and exhibiting robust generalization across diverse embodiments and scenarios. To further validate the effectiveness and generality of our method, we present a compact VLA model based on 4B Phi-3-Vision, pretrained on the Open-X-Embodiment and finetuned on our dataset, rivals the 7B OpenVLA baseline while significantly improving inference efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10345
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies
Zheng, Ruijie
Liang, Yongyuan
Huang, Shuaiyi
Gao, Jianfeng
Daumé III, Hal
Kolobov, Andrey
Huang, Furong
Yang, Jianwei
Robotics
Artificial Intelligence
Although large vision-language-action (VLA) models pretrained on extensive robot datasets offer promising generalist policies for robotic learning, they still struggle with spatial-temporal dynamics in interactive robotics, making them less effective in handling complex tasks, such as manipulation. In this work, we introduce visual trace prompting, a simple yet effective approach to facilitate VLA models' spatial-temporal awareness for action prediction by encoding state-action trajectories visually. We develop a new TraceVLA model by finetuning OpenVLA on our own collected dataset of 150K robot manipulation trajectories using visual trace prompting. Evaluations of TraceVLA across 137 configurations in SimplerEnv and 4 tasks on a physical WidowX robot demonstrate state-of-the-art performance, outperforming OpenVLA by 10% on SimplerEnv and 3.5x on real-robot tasks and exhibiting robust generalization across diverse embodiments and scenarios. To further validate the effectiveness and generality of our method, we present a compact VLA model based on 4B Phi-3-Vision, pretrained on the Open-X-Embodiment and finetuned on our dataset, rivals the 7B OpenVLA baseline while significantly improving inference efficiency.
title TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2412.10345