A Dual Process VLA: Efficient Robotic Manipulation Leveraging VLM
This addresses the problem of computational inefficiency in robotic manipulation for researchers and practitioners, offering a scalable solution, though it appears incremental as it builds on existing VLA models with a novel hierarchical approach.
The paper tackles the challenge of achieving efficient real-time performance in Vision-Language-Action (VLA) models for robotic manipulation by proposing DP-VLA, a hierarchical framework that reduces computational overhead and improves task execution, achieving faster inference and higher success rates on the RoboCasa dataset.
Vision-Language-Action (VLA) models are receiving increasing attention for their ability to enable robots to perform complex tasks by integrating visual context with linguistic commands. However, achieving efficient real-time performance remains challenging due to the high computational demands of existing models. To overcome this, we propose Dual Process VLA (DP-VLA), a hierarchical framework inspired by dual-process theory. DP-VLA utilizes a Large System 2 Model (L-Sys2) for complex reasoning and decision-making, while a Small System 1 Model (S-Sys1) handles real-time motor control and sensory processing. By leveraging Vision-Language Models (VLMs), the L-Sys2 operates at low frequencies, reducing computational overhead, while the S-Sys1 ensures fast and accurate task execution. Experimental results on the RoboCasa dataset demonstrate that DP-VLA achieves faster inference and higher task success rates, providing a scalable solution for advanced robotic applications.