Language Embedded Radiance Fields for Zero-Shot Task-Oriented Grasping
This addresses the challenge of scaling object diversity for robotic grasping by enabling zero-shot, language-guided part-specific grasps, which is incremental as it builds on existing methods like LERF and DINO.
The paper tackles the problem of task-oriented grasping by specific object parts without training on part data, proposing LERF-TOGO, which uses vision-language models zero-shot to output grasp distributions based on natural language queries, achieving 81% correct part selection and 69% successful grasps on 31 objects.
Grasping objects by a specific part is often crucial for safety and for executing downstream tasks. Yet, learning-based grasp planners lack this behavior unless they are trained on specific object part data, making it a significant challenge to scale object diversity. Instead, we propose LERF-TOGO, Language Embedded Radiance Fields for Task-Oriented Grasping of Objects, which uses vision-language models zero-shot to output a grasp distribution over an object given a natural language query. To accomplish this, we first reconstruct a LERF of the scene, which distills CLIP embeddings into a multi-scale 3D language field queryable with text. However, LERF has no sense of objectness, meaning its relevancy outputs often return incomplete activations over an object which are insufficient for subsequent part queries. LERF-TOGO mitigates this lack of spatial grouping by extracting a 3D object mask via DINO features and then conditionally querying LERF on this mask to obtain a semantic distribution over the object with which to rank grasps from an off-the-shelf grasp planner. We evaluate LERF-TOGO's ability to grasp task-oriented object parts on 31 different physical objects, and find it selects grasps on the correct part in 81% of all trials and grasps successfully in 69%. See the project website at: lerftogo.github.io