# Monocular 3D Object Position Estimation with VLMs for Human-Robot Interaction

arXiv: https://arxiv.org/abs/2603.01224 · HTML: https://mlsanity.com/paper/2603.01224/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 16 of its 16 references that are in the map.
- First posted on arXiv 1 Mar 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 16 of 16)

- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [LERF: Language Embedded Radiance Fields](https://mlsanity.com/paper/2303.09553/) (2023)
- [CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation](https://mlsanity.com/paper/2411.19650/) (2024)
- [Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models](https://mlsanity.com/paper/2409.17146/) (2024)
- [RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics](https://mlsanity.com/paper/2406.10721/) (2024)
- [Foundation Models in Robotics: Applications, Challenges, and the Future](https://mlsanity.com/paper/2312.07843/) (2023)
- [MOKA: Open-World Robotic Manipulation through Mark-Based Visual Prompting](https://mlsanity.com/paper/2403.03174/) (2024)
- [Language Embedded Radiance Fields for Zero-Shot Task-Oriented Grasping](https://mlsanity.com/paper/2309.07970/) (2023)
- [MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection](https://mlsanity.com/paper/2203.13310/) (2022)
- [Robotic Applications of Pre-Trained Vision-Language Models to Various Recognition Behaviors](https://mlsanity.com/paper/2303.05674/) (2023)
- [Lifelong LERF: Local 3D Semantic Inventory Monitoring Using FogROS2](https://mlsanity.com/paper/2403.10494/) (2024)
- [Vision Foundation Model Driven Foreground-Aware Pseudo-LiDAR Generation for Monocular 3D Object Detection](https://mlsanity.com/paper/2404.09431/) (2024)
- [Bringing the RT-1-X Foundation Model to a SCARA robot](https://mlsanity.com/paper/2409.03299/) (2024)

## Abstract (arXiv)

Pre-trained general-purpose Vision-Language Models (VLM) hold the potential to enhance intuitive human-machine interactions due to their rich world knowledge and 2D object detection capabilities. However, VLMs for 3D coordinates detection tasks are rare. In this work, we investigate interactive abilities of VLMs by returning 3D object positions given a monocular RGB image from a wrist-mounted camera, natural language input, and robot states. We collected and curated a heterogeneous dataset of more than 100,000 images and finetuned a VLM using QLoRA with a custom regression head. By implementing conditional routing, our model maintains its ability to process general visual queries while adding specialized 3D position estimation capabilities. Our results demonstrate robust predictive performance with a median MAE of 13 mm on the test set and a five-fold improvement over a simpler baseline without finetuning. In about 25% of the cases, predictions are within a range considered acceptable for the robot to interact with objects.