From Words to Poses: Enhancing Novel Object Pose Estimation with Vision Language Models
This work addresses the challenge of enabling robots to adapt to new objects in real-world scenarios, though it appears incremental by applying existing VLMs to a specific robotics task.
The authors tackled the problem of zero-shot 6D object pose estimation for novel objects by leveraging vision language models, achieving pose estimation without prior knowledge through a framework that uses language embeddings and NeRF reconstructions.
Robots are increasingly envisioned to interact in real-world scenarios, where they must continuously adapt to new situations. To detect and grasp novel objects, zero-shot pose estimators determine poses without prior knowledge. Recently, vision language models (VLMs) have shown considerable advances in robotics applications by establishing an understanding between language input and image input. In our work, we take advantage of VLMs zero-shot capabilities and translate this ability to 6D object pose estimation. We propose a novel framework for promptable zero-shot 6D object pose estimation using language embeddings. The idea is to derive a coarse location of an object based on the relevancy map of a language-embedded NeRF reconstruction and to compute the pose estimate with a point cloud registration method. Additionally, we provide an analysis of LERF's suitability for open-set object pose estimation. We examine hyperparameters, such as activation thresholds for relevancy maps and investigate the zero-shot capabilities on an instance- and category-level. Furthermore, we plan to conduct robotic grasping experiments in a real-world setting.