Lightweight Language-driven Grasp Detection using Conditional Consistency Model

Language-driven grasp detection is a fundamental yet challenging task in robotics with various industrial applications. This work presents a new approach for language-driven grasp detection that leverages lightweight diffusion models to achieve fast inference time. By integrating diffusion processes with grasping prompts in natural language, our method can effectively encode visual and textual information, enabling more accurate and versatile grasp positioning that aligns well with the text query. To overcome the long inference time problem in diffusion models, we leverage the image and text features as the condition in the consistency model to reduce the number of denoising timesteps during inference. The intensive experimental results show that our method outperforms other recent grasp detection methods and lightweight diffusion models by a clear margin. We further validate our method in real-world robotic experiments to demonstrate its fast inference time capability.

Authors

• Nghia Nguyen
• Minh Nhat Vu
• Baoru Huang
• An Vuong
• Ngan Le
• Thieu Vo
• Anh Nguyen 0003

Keywords

• Visualization
• Accuracy
• Service robots
• Noise reduction
• Natural languages
• Diffusion processes
• Grasping
• Diffusion models
• Intelligent robots
• Denoising
• Image Features
• Natural Language
• Diffusion Process
• Diffusion Model
• Surgical Margins
• Inference Time
• Robotic Tasks
• Text Query
• Neural Network
• Convolutional Neural Network
• Input Image
• Scoring Function
• Language Teaching
• Point Cloud
• Robotic System
• Time Index
• Robotic Applications
• Language Status
• Text Encoder
• Inference Speed
• Zero-shot
• 3D Point Cloud
• Foundation Model