Translating Natural Language Instructions to Computer Programs for Robot Manipulation

TL;DR

This paper introduces a method for translating natural language instructions into Python programs that control robots, enabling better understanding and execution of tasks by incorporating non-differentiable modules and more informative labels.

Contribution

The paper proposes translating natural language instructions into executable Python functions for robot control, improving over direct action prediction methods.

Findings

Outperforms direct action prediction models

Utilizes non-differentiable modules like constraint solvers

Uses informative program labels capturing task intent

Abstract

It is highly desirable for robots that work alongside humans to be able to understand instructions in natural language. Existing language conditioned imitation learning models directly predict the actuator commands from the image observation and the instruction text. Rather than directly predicting actuator commands, we propose translating the natural language instruction to a Python function which queries the scene by accessing the output of the object detector and controls the robot to perform the specified task. This enables the use of non-differentiable modules such as a constraint solver when computing commands to the robot. Moreover, the labels in this setup are significantly more informative computer programs that capture the intent of the expert rather than teleoperated demonstrations. We show that the proposed method performs better than training a neural network to directly predict the robot actions.