Lorenzo Jamone

James: A Humanoid Robot Acting over an Unstructured World

The recent trend of humanoid robotics research has been deeply influenced by concepts such as embodiment, embodied interaction and emergence. In our view, these concepts, beside shaping the controlling intelligence, should guide the very design process of the modern humanoid robotic platforms. In this paper, we discuss how these principles have been applied to the design of a humanoid robot called James. James has been designed by considering an object manipulation scenario and by explicitly taking into account embodiment, interaction, and the exploitation of smart design solutions. The robot is equipped with moving eyes, neck, arm and hand, and a rich set of sensors, enabling proprioceptive, kinesthetic, tactile and visual sensing. A great deal of effort has been devoted to the design of the hand and touch sensors. Experiments, e.g., tactile object classification, have been performed, to validate the quality of the robot perceptual capabilities

AUTONOMOUS ONLINE LEARNING OF REACHING BEHAVIOR IN A HUMANOID ROBOT

In this paper we describe an autonomous strategy which enables a humanoid robot to learn how to reach for a visually identified object in the 3D space. The robot is a 22-DOF upper-body humanoid wit...

Highly sensitive soft tactile sensors for an anthropomorphic robotic hand

This paper describes the design and realization of novel tactile sensors based on soft materials and magnetic sensing. In particular, the goal was to realize: 1) soft; 2) robust; 3) small; and 4) low-cost sensors that can be easily fabricated and integrated on robotic devices that interact with the environment. We targeted a number of desired features, the most important being: 1) high sensitivity; 2) low hysteresis; and 3) repeatability. The sensor consists of a silicone body in which a small magnet is immersed; an Hall-effect sensor placed below the silicone body measures the magnetic field generated by the magnet, which changes when the magnet is displaced due to an applied external pressure. Two different versions of the sensor have been manufactured, characterized, and mounted on an anthropomorphic robotic hand. Experiments, in which the hand interacts with real-world objects, are reported.

Cross-cultural study on human-robot greeting interaction : acceptance and discomfort by Egyptians and Japanese

Abstract As witnessed in several behavioural studies, a complex relationship exists between people’s cultural background and their general acceptance towards robots. However, very few studies have investigated whether a robot’s original language and gesture based on certain culture have an impact on the people of the different cultures. The purpose of this work is to provide experimental evidence which supports the idea that humans may accept more easily a robot that can adapt to their specific culture. Indeed, improving acceptance and reducing discomfort is fundamental for future deployment of robots as assistive, health-care or companion devices into a society. We conducted a Human- Robot Interaction experiment both in Egypt and in Japan. Human subjects were engaged in a simulated video conference with robots that were greeting and speaking either in Arabic or in Japanese. The subjects completed a questionnaire assessing their preferences and their emotional state, while their spontaneous reactions were recorded in different ways. The results suggest that Egyptians prefer the Arabic robot, while they feel a sense of discomfort when interacting with the Japanese robot; the opposite is also true for the Japanese. These findings confirm the importance of the localisation of a robot in order to improve human acceptance during social human-robot interaction.

Accurate control of a human-like tendon-driven neck

In this paper we describe the actuation and control of a humanoid robot neck. Particular attention will be posed on the description of the neck actuation structure, whose design has a noticeable human similarity. Specifically, the final mechanical design was inspired by the human skeleton, with the neck bone movements constrained and actuated by the surrounding muscles. In our robotic platform, the neck bone was realized with a steel spring surrounded by steel tendons in place of muscles. The specific and innovative mechanical design have imposed the design of a non-standard actuation structure which, in turn, have lead to an innovative control scheme. The main focus of the paper will be on describing different control schemes and discussing their performances in details.

Design and Characterization of a Three-Axis Hall Effect-Based Soft Skin Sensor

This paper presents an easy means to produce a 3-axis Hall effect–based skin sensor for robotic applications. It uses an off-the-shelf chip and is physically small and provides digital output. Furthermore, the sensor has a soft exterior for safe interactions with the environment; in particular it uses soft silicone with about an 8 mm thickness. Tests were performed to evaluate the drift due to temperature changes, and a compensation using the integral temperature sensor was implemented. Furthermore, the hysteresis and the crosstalk between the 3-axis measurements were evaluated. The sensor is able to detect minimal forces of about 1 gf. The sensor was calibrated and results with total forces up to 1450 gf in the normal and tangential directions of the sensor are presented. The test revealed that the sensor is able to measure the different components of the force vector.

Learning task space control through goal directed exploration

We present an autonomous goal-directed strategy to learn how to control a redundant robot in the task space. We discuss the advantages of exploring the state space through goal-directed actions defined in the task space (i.e. learning by trying to do) instead of performing motor babbling in the joints space, and we stress the importance of learning to be performed online, without any separation between training and execution. Our solution relies on learning the forward model and then inverting it for the control; different approaches to learn the forward model are described and compared. Experimental results on a simulated humanoid robot are provided to support our claims. The robot learns autonomously how to perform reaching actions directed toward 3D targets in task space by using arm and waist motion, not relying on any prior knowledge or initial motor babbling. To test the ability of the system to adapt to sudden changes both in the robot structure and in the perceived environment we artificially introduce two different kinds of kinematic perturbations: a modification of the length of one link and a rotation of the task space reference frame. Results demonstrate that the online update of the model allows the robot to cope with such situations.

Affordances in Psychology, Neuroscience, and Robotics: A Survey

The concept of affordances appeared in psychology during the late 60s as an alternative perspective on the visual perception of the environment. It was revolutionary in the intuition that the way living beings perceive the world is deeply influenced by the actions they are able to perform. Then, across the last 40 years, it has influenced many applied fields, e.g., design, human-computer interaction, computer vision, and robotics. In this paper, we offer a multidisciplinary perspective on the notion of affordances. We first discuss the main definitions and formalizations of the affordance theory, then we report the most significant evidence in psychology and neuroscience that support it, and finally we review the most relevant applications of this concept in robotics.

Machine-learning based control of a human-like tendon-driven neck

This paper describes the control of a human-like robotic neck actuated with tendons. The controller regulates the length of the tendons to achieve a desired orientation of the neck and at the same time it maintains the tension of the tendons within certain limits. The solution we propose does not use any model of the system, but it relies on online learning of the different Jacobian mappings required by the controller. Learning, data acquisition and control are simultaneous; thus learning is completely autonomous, and purely online. We show that after enough iterations the controller produces straight trajectories in the task space and is able to maintain the tension of the tendons within safe limits.

Learning to Exploit Proximal Force Sensing: A Comparison Approach

We present an evaluation of different techniques for the estimation of forces and torques measured by a single six-axis force/torque sensor placed along the kinematic chain of a humanoid robot arm. In order to retrieve the external forces and detect possible contact situations, the internal forces must be estimated. The prediction performance of an analytically derived dynamic model as well as two supervised machine learning techniques, namely Least Squares Support Vector Machines and Neural Networks, are investigated on this problem. The performance are evaluated on the normalized mean square error (NMSE) and the comparison is made with respect to the dimension of the training set, the information contained in the input space and, finally, using a Euclidean subsampling strategy.