# Learning from Implicit Information in Natural Language Instructions for Robotic Manipulations

## TL;DR

This paper introduces a Bayesian learning approach to improve the grounding of natural language instructions in robotic manipulation by resolving inconsistencies between learned world representations and language grounding, demonstrated on a robotic arm scenario.

## Contribution

It proposes a novel Bayesian method to align separate learned representations of language and world models in robotics, addressing data scarcity and inconsistency issues.

## Key findings

- Bayesian learning effectively resolves grounding inconsistencies.
- Approach demonstrates feasibility on a physical robotic arm.
- Implicit spatio-relational information enhances instruction understanding.

## Abstract

Human-robot interaction often occurs in the form of instructions given from a human to a robot. For a robot to successfully follow instructions, a common representation of the world and objects in it should be shared between humans and the robot so that the instructions can be grounded. Achieving this representation can be done via learning, where both the world representation and the language grounding are learned simultaneously. However, in robotics this can be a difficult task due to the cost and scarcity of data. In this paper, we tackle the problem by separately learning the world representation of the robot and the language grounding. While this approach can address the challenges in getting sufficient data, it may give rise to inconsistencies between both learned components. Therefore, we further propose Bayesian learning to resolve such inconsistencies between the natural language grounding and a robot's world representation by exploiting spatio-relational information that is implicitly present in instructions given by a human. Moreover, we demonstrate the feasibility of our approach on a scenario involving a robotic arm in the physical world.