How to select and use tools? : Active Perception of Target Objects Using Multimodal Deep Learning

TL;DR

This paper presents a multimodal deep learning approach enabling robots to recognize objects and their characteristics, learn tool-object-action relations, and perform tool selection and handling in domestic tasks.

Contribution

It introduces a deep neural network model that integrates multimodal sensorimotor data for active perception and tool use, improving adaptability to unknown objects.

Findings

Robot successfully recognizes object characteristics and servings with unknown ingredients.

Multimodal data enhances perception for tool use.

The model effectively generates motions for tool selection and handling.

Abstract

Selection of appropriate tools and use of them when performing daily tasks is a critical function for introducing robots for domestic applications. In previous studies, however, adaptability to target objects was limited, making it difficult to accordingly change tools and adjust actions. To manipulate various objects with tools, robots must both understand tool functions and recognize object characteristics to discern a tool-object-action relation. We focus on active perception using multimodal sensorimotor data while a robot interacts with objects, and allow the robot to recognize their extrinsic and intrinsic characteristics. We construct a deep neural networks (DNN) model that learns to recognize object characteristics, acquires tool-object-action relations, and generates motions for tool selection and handling. As an example tool-use situation, the robot performs an ingredients transfer task, using a turner or ladle to transfer an ingredient from a pot to a bowl. The results confirm that the robot recognizes object characteristics and servings even when the target ingredients are unknown. We also examine the contributions of images, force, and tactile data and show that learning a variety of multimodal information results in rich perception for tool use.