DobotTrack: Target-Grounded Vision-Language-Action Learning for Embodied Person Tracking
DobotTrack: Target-Grounded Vision-Language-Action Learning for Embodied Person Tracking
This paper introduces DobotTrack, a target-grounded vision-language-action (VLA) framework designed for embodied person tracking.
The authors present DobotTrack, a vision-language-action framework for embodied person tracking that integrates auxiliary grounding supervision and temporal modeling, reporting an average success rate of 77.9% on EVT-Bench with a 0.8B-parameter model and introducing a real-world dataset collected from a quadruped robot containing 126 episodes and 596,323 mask-annotated frames.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
Reported success rate
77.9%
Reported trials
View original evidence
erve identity-discriminative appearance features and spatial cues in compact historical tokens. On EVT-Bench, our 0.8B-parameter model achieves an average success rate of 77.9%, exceeding OmTrackVLA by 16.9 percentage points across the three tasks. We further construct a real-world person-tracking dataset collected using a quadruped robot, comprising 126 episodes and 596,323 mask-annotated frames. The target masks en
Open source S4episodes
126 episodes
Reported trials
View original evidence
erve identity-discriminative appearance features and spatial cues in compact historical tokens. On EVT-Bench, our 0.8B-parameter model achieves an average success rate of 77.9%, exceeding OmTrackVLA by 16.9 percentage points across the three tasks. We further construct a real-world person-tracking dataset collected using a quadruped robot, comprising 126 episodes and 596,323 mask-annotated frames. The target masks en
Open source S4frames
596,323
View original evidence
erve identity-discriminative appearance features and spatial cues in compact historical tokens. On EVT-Bench, our 0.8B-parameter model achieves an average success rate of 77.9%, exceeding OmTrackVLA by 16.9 percentage points across the three tasks. We further construct a real-world person-tracking dataset collected using a quadruped robot, comprising 126 episodes and 596,323 mask-annotated frames. The target masks en
Open source S4
- code: Available Artifact link Open source S5
- dataset: not_reported
- paper: not_reported
- weights: not_reported
- code: not_reported
What remains unknown
Not established in the collected evidence: Environment, Control, Data origin.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
arXiv:2611.09041v1 Announce Type: new Abstract: Language-guided embodied person tracking requires a mobile agent to identify a target from a referring description and consistently follow the target under egocentric observations. We present DobotTrack, a target-grounded vision-language-action (VLA) framework that integrates auxiliary grounding supervision with efficient temporal modeling. We systematically investigate
Open source S2
erve identity-discriminative appearance features and spatial cues in compact historical tokens. On EVT-Bench, our 0.8B-parameter model achieves an average success rate of 77.9%, exceeding OmTrackVLA by 16.9 percentage points across the three tasks. We further construct a real-world person-tracking dataset collected using a quadruped robot, comprising 126 episodes and 596,323 mask-annotated frames. The target masks en
Open source S4
DobotTrack: Target-Grounded Vision-Language-Action Learning for Embodied Person Tracking
Open source S1
able automatic derivation of bounding boxes and visual-spatial labels encoding horizontal position and apparent image scale, providing additional grounding supervision without separate manual annotation of these labels. Together, our framework and annotation pipeline support learning target-grounded tracking policies from simulated and real-world data. Code is available at https://github.com/Dobot-Team/dobot_track.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org