---
title: 'PerAct: Transformer for Robotics'
url: https://www.emergentmind.com/topics/peract
type: topic
---

# PerAct: Transformer for Robotics

PerAct, short for **Perceiver-Actor**, is a language-conditioned, multi-task behavior-cloning agent for **6-DoF robotic manipulation** that encodes **RGB-D voxel observations** and **language goals** with a **Perceiver Transformer**, then predicts discretized actions by **“detecting the next best voxel action”** [2209.05451]. It was introduced to test whether transformer-based formulations can remain effective in robotic manipulation despite the limited and expensive nature of manipulation data, and it does so by imposing a structured **3D voxelized observation and action space** rather than learning a direct unstructured image-to-action mapping [2209.05451]. In the reported experiments, a single model is trained for **18 RLBench tasks with 249 variations** and **7 real-world tasks with 18 variations** from only a few demonstrations per task, and it is reported to significantly outperform both unstructured image-to-action agents and 3D ConvNet baselines across a broad set of tabletop tasks [2209.05451].

## 1. Origin and problem formulation

PerAct was introduced in **“Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation”** [2209.05451] as a response to a central tension in robot learning: transformers have scaled effectively in vision and natural language processing, but robotic manipulation typically lacks the large, cheap datasets that support such scaling elsewhere. The method therefore does not simply transplant a vision transformer into manipulation

Source: https://www.emergentmind.com/topics/peract