About: REEM is a research topic. Over the lifetime, 17 publications have been published within this topic receiving 173 citations. The topic is also known as: REEM-C.
TL;DR: This paper introduces the humanoid robot Reem-B, built by Pal robotics as a research platform in the field of service robots, which has been improved from other robots at three different levels: with an increased battery life, with the ability to autonomously navigate in indoor environments while avoiding obstacles, and by integrating all the control systems within the robot itself.
Abstract: This paper introduces the humanoid robot Reem-B, built by Pal robotics as a research platform in the field of service robots. The idea is to produce robots that can help humans and cohabit their environments. For this purpose, the body plan, sensory and actuator system of the robot, as well as its cognitive abilities must be designed to perform real-world tasks including dynamic walking, interaction with people or object recognition and manipulation. Reem-B achieves this scope by using two legs, two strong arms with fingered hands, and a software suite that controls all its degrees of freedom, coordinating them with vision and auditory systems. The main difference with other humanoids of its size is its level of autonomy. Autonomy in this robot has been improved from other robots at three different levels: with an increased battery life (estimated twice of the competitors), with the ability to autonomously navigate in indoor environments while avoiding obstacles, and by integrating all the control systems within the robot itself.
TL;DR: The proposed SOAR cognitive architecture allows to include new goals for the robot just by adding new skills (without the need to encode new plans), and has been tested on a human-sized humanoid robot, REEM, acting as a general purpose service robot.
Abstract: A humanoid service robot equipped with a set of simple action skills including navigating, grasping, recognising objects or people, among others, is considered in this paper. By using those skills the robot should complete a voice command expressed in natural language encoding a complex task defined as the concatenation of a number of those basic skills. As a main feature, no traditional planner has been used to decide skills to be activated, as well as in which sequence. Instead, the SOAR cognitive architecture acts as the reasoner by selecting which action the robot should complete, addressing it towards the goal. Our proposal allows to include new goals for the robot just by adding new skills without the need to encode new plans. The proposed architecture has been tested on a human-sized humanoid robot, REEM, acting as a general purpose service robot.
TL;DR: REEM is a humanoid service robot designed to provide useful applications in public spaces and to assist people in domestic environments using autonomous navigation, person detection and recognition, speech synthesis and recognition.
Abstract: REEM is a humanoid service robot designed to provide useful applications in public spaces and to assist people in domestic environments. REEM is the result of several years of research in real scenarios. Its main functionalities are autonomous navigation, person detection and recognition, speech synthesis and recognition.
TL;DR: In this article, an approach for modelling and implementation of autonomous humanoid system's behaviour is presented, which can be used to support guided tours through exhibitions, museums, art centres, innovative labs, etc.
Abstract: This paper presents an approach for modelling and implementation of autonomous humanoid system’s behaviour. The main objective of our project was to analyse possible interaction scenarios between humans and autonomous robots, and to elaborate a framework for providing flexible guided tour options, utilising the features of humanoid PAL REEM robot. The framework can be used to support guided tours through exhibitions, museums, art centres, innovative labs, etc. We introduce the core results of the project and briefly discuss our future work. There are many scenarios where humans interactively conduct some joint activities. Using our approach, presented here, one of the parties could be replaced by humanoid robots. State of the art technology in voice recognition and generation, as well as path planning were used to achieve requested research objectives.
TL;DR: Several experiments are provided illustrating how knowledge is acquired by the robot, represented in the form of dynamical systems, generalized and reproduced from different starting conditions.