VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Kui, Xu, Shuhang, Chen, Hao, Wang, Churan, Li, Zhoujun, Wang, Yizhou, Zhong, Fangwei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909625868091392
author Wu, Kui
Xu, Shuhang
Chen, Hao
Wang, Churan
Li, Zhoujun
Wang, Yizhou
Zhong, Fangwei
author_facet Wu, Kui
Xu, Shuhang
Chen, Hao
Wang, Churan
Li, Zhoujun
Wang, Yizhou
Zhong, Fangwei
contents We introduce a novel self-improving framework that enhances Embodied Visual Tracking (EVT) with Vision-Language Models (VLMs) to address the limitations of current active visual tracking systems in recovering from tracking failure. Our approach combines the off-the-shelf active tracking methods with VLMs' reasoning capabilities, deploying a fast visual policy for normal tracking and activating VLM reasoning only upon failure detection. The framework features a memory-augmented self-reflection mechanism that enables the VLM to progressively improve by learning from past experiences, effectively addressing VLMs' limitations in 3D spatial reasoning. Experimental results demonstrate significant performance improvements, with our framework boosting success rates by $72\%$ with state-of-the-art RL-based approaches and $220\%$ with PID-based methods in challenging environments. This work represents the first integration of VLM-based reasoning to assist EVT agents in proactive failure recovery, offering substantial advances for real-world robotic applications that require continuous target monitoring in dynamic, unstructured environments. Project website: https://sites.google.com/view/evt-recovery-assistant.
format Preprint
id arxiv_https___arxiv_org_abs_2505_20718
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language Models
Wu, Kui
Xu, Shuhang
Chen, Hao
Wang, Churan
Li, Zhoujun
Wang, Yizhou
Zhong, Fangwei
Computer Vision and Pattern Recognition
Artificial Intelligence
We introduce a novel self-improving framework that enhances Embodied Visual Tracking (EVT) with Vision-Language Models (VLMs) to address the limitations of current active visual tracking systems in recovering from tracking failure. Our approach combines the off-the-shelf active tracking methods with VLMs' reasoning capabilities, deploying a fast visual policy for normal tracking and activating VLM reasoning only upon failure detection. The framework features a memory-augmented self-reflection mechanism that enables the VLM to progressively improve by learning from past experiences, effectively addressing VLMs' limitations in 3D spatial reasoning. Experimental results demonstrate significant performance improvements, with our framework boosting success rates by $72\%$ with state-of-the-art RL-based approaches and $220\%$ with PID-based methods in challenging environments. This work represents the first integration of VLM-based reasoning to assist EVT agents in proactive failure recovery, offering substantial advances for real-world robotic applications that require continuous target monitoring in dynamic, unstructured environments. Project website: https://sites.google.com/view/evt-recovery-assistant.
title VLM Can Be a Good Assistant: Enhancing Embodied Visual Tracking with Self-Improving Vision-Language Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2505.20718