robotics-transformer1.github.io - RT-1: Robotics Transformer

home > domains > robotics-transformer1.github.io

Description: RT-1: Robotics Transformer

Example domain paragraphs

By transferring knowledge from large, diverse, task-agnostic datasets, modern machine learning models can enable solving specific downstream tasks either zero-shot or with small task-specific datasets to a high level of performance. While this capability has been demonstrated in other fields such as computer vision, natural language processing or speech recognition, it remains to be shown in robotics, where the generalization and fine-tuning capabilities of the models are particularly critical due to the di

RT-1 shows better performance and generalization thanks to its ability to absorb a large amount of diverse data, including robot trajectories with multiple tasks, objects and environments. Baseline approaches exhibit limited ability to fully utilize large datasets.

In the past few years, we have seen powerful machine learning models that achieve significant generalization capabilities by absorbing large amounts of data. For example, large language models such as PaLM or GPT-3 can generalize to many tasks such as language understanding, code completion or arithmetic, especially as their number of parameters increase. Importantly, these large models have the ability to effectively absorb large amounts of diverse data. In the case of large language models that data being

Links to robotics-transformer1.github.io (4)

• tedxiao.me Ted Xiao - Google DeepMind
• robotics-transformer2.github.io RT-2: Vision-Language-Action Models
• rt-trajectory.github.io Robotic Task Generalization via Hindsight Trajectory Sketches
• txizzle.github.io Ted Xiao - Google DeepMind