What is the impact of scaling the training dataset size on the zero-shot task-solving accuracy of RT-1 when te

Amid growing efforts to leverage advances in large language models (LLMs) and visionlanguage models (VLMs) for robotics, Vision-Language-Action (VLA) models have recently gained significant attention. By unifying vision, language, and action data at scale, which have traditionally been studied separately, VLA models aim to learn policies that generalise across diverse tasks, objects, embodiments, and environments. This generalisation capability is expected to enable robots to solve novel downstream tasks with minimal or no additional task-specific data, facilitating more flexible and scalable

Research goal: What is the impact of scaling the training dataset size on the zero-shot task-solving accuracy of RT-1 when tested on the RoboTHOR benchmark, and how does this compare to models trained with reinforcement learning?

Autonomous synthesis report generated by SOVEREIGN Research Kernel. Tribunal consensus score: 7.8/10.