ActivePose: Active 6D Object Pose Estimation and Tracking for Robotic Manipulation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914376979578880 |
|---|---|
| author | Liu, Sheng Li, Zhe Wang, Weiheng Sun, Han Zhang, Heng Chen, Hongpeng Qin, Yusen Ajoudani, Arash Wang, Yizhao |
| author_facet | Liu, Sheng Li, Zhe Wang, Weiheng Sun, Han Zhang, Heng Chen, Hongpeng Qin, Yusen Ajoudani, Arash Wang, Yizhao |
| contents | Accurate 6-DoF object pose estimation and tracking are critical for reliable robotic manipulation. However, zero-shot methods often fail under viewpoint-induced ambiguities and fixed-camera setups struggle when objects move or become self-occluded. To address these challenges, we propose an active pose estimation pipeline that combines a Vision-Language Model (VLM) with "robotic imagination" to dynamically detect and resolve ambiguities in real time. In an offline stage, we render a dense set of views of the CAD model, compute the FoundationPose entropy for each view, and construct a geometric-aware prompt that includes low-entropy (unambiguous) and high-entropy (ambiguous) examples. At runtime, the system: (1) queries the VLM on the live image for an ambiguity score; (2) if ambiguity is detected, imagines a discrete set of candidate camera poses by rendering virtual views, scores each based on a weighted combination of VLM ambiguity probability and FoundationPose entropy, and then moves the camera to the Next-Best-View (NBV) to obtain a disambiguated pose estimation. Furthermore, since moving objects may leave the camera's field of view, we introduce an active pose tracking module: a diffusion-policy trained via imitation learning, which generates camera trajectories that preserve object visibility and minimize pose ambiguity. Experiments in simulation and real-world show that our approach significantly outperforms classical baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_11364 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ActivePose: Active 6D Object Pose Estimation and Tracking for Robotic Manipulation Liu, Sheng Li, Zhe Wang, Weiheng Sun, Han Zhang, Heng Chen, Hongpeng Qin, Yusen Ajoudani, Arash Wang, Yizhao Robotics Accurate 6-DoF object pose estimation and tracking are critical for reliable robotic manipulation. However, zero-shot methods often fail under viewpoint-induced ambiguities and fixed-camera setups struggle when objects move or become self-occluded. To address these challenges, we propose an active pose estimation pipeline that combines a Vision-Language Model (VLM) with "robotic imagination" to dynamically detect and resolve ambiguities in real time. In an offline stage, we render a dense set of views of the CAD model, compute the FoundationPose entropy for each view, and construct a geometric-aware prompt that includes low-entropy (unambiguous) and high-entropy (ambiguous) examples. At runtime, the system: (1) queries the VLM on the live image for an ambiguity score; (2) if ambiguity is detected, imagines a discrete set of candidate camera poses by rendering virtual views, scores each based on a weighted combination of VLM ambiguity probability and FoundationPose entropy, and then moves the camera to the Next-Best-View (NBV) to obtain a disambiguated pose estimation. Furthermore, since moving objects may leave the camera's field of view, we introduce an active pose tracking module: a diffusion-policy trained via imitation learning, which generates camera trajectories that preserve object visibility and minimize pose ambiguity. Experiments in simulation and real-world show that our approach significantly outperforms classical baselines. |
| title | ActivePose: Active 6D Object Pose Estimation and Tracking for Robotic Manipulation |
| topic | Robotics |
| url | https://arxiv.org/abs/2509.11364 |