DobotTrack: Target-Grounded Vision-Language-Action Learning for Embodied Person Tracking
cs.RO, cs.CV
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/Dobot-Team/dobot_track
Terminology
Sources
- Follow Anything: Open-set detection, tracking, and following in real-time
- RSPT: Reconstruct Surroundings and Predict Trajectories for Generalizable Active Object Tracking
- Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks
- TrackVLA: Embodied Visual Tracking in the Wild
- TrackVLA++: Unleashing Reasoning and Memory Capabilities in VLA Models for Embodied Visual Tracking
- ReferTrack: Referring Then Tracking for Embodied Visual Tracking
- Person Re-Identification for Robot Person Following with Online Continual Learning
- InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models
- TPT-Bench: A Large-Scale, Long-Term and Robot-Egocentric Dataset for Benchmarking Target Person Tracking
- Empowering Embodied Visual Tracking with Visual Foundation Models and Offline RL
- Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
- Kosmos-2: Grounding Multimodal Large Language Models to the World
- SAM 2: Segment Anything in Images and Videos
- LISA: Reasoning Segmentation via Large Language Model
- MOTR: End-to-End Multiple-Object Tracking with Transformer
- XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
- VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memory
- LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models
- LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding
- BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation