A Hybrid SLAM and Object Recognition System for Pepper Robot

TL;DR

This paper presents a hybrid SLAM and object recognition system integrated with the Pepper robot, enabling autonomous indoor mapping and object localization using ORB SLAM 2 and SIFT-RANSAC techniques, demonstrated in real-world scenarios.

Contribution

The paper introduces a novel hybrid system combining SLAM and object recognition specifically for the Pepper robot in real-world indoor environments.

Findings

System successfully maps indoor environments with Pepper.

Object recognition and localization are effective in real-world tests.

Source code is publicly available for community use.

Abstract

Humanoid robots are playing increasingly important roles in real-life tasks especially when it comes to indoor applications. Providing robust solutions for the tasks such as indoor environment mapping, self-localisation and object recognition are essential to make the robots to be more autonomous, hence, more human-like. The well-known Aldebaran service robot Pepper is a suitable candidate for achieving these goals. In this paper, a hybrid system combining Simultaneous Localisation and Mapping (SLAM) algorithm with object recognition is developed and tested with Pepper robot in real-world conditions for the first time. The ORB SLAM 2 algorithm was taken as a seminal work in our research. Then, an object recognition technique based on Scale-Invariant Feature Transform (SIFT) and Random Sample Consensus (RANSAC) was combined with SLAM to recognise and localise objects in the mapped indoor environment. The results of our experiments showed the system's applicability for the Pepper robot in real-world scenarios. Moreover, we made our source code available for the community at https://github.com/PaolaArdon/Salt-Pepper.