International Journal of Humanoid Robotics

One of the most promising approaches to understand human cognitive and developmental mechanisms is a synthetic approach using humanoid robots; an approach to understand the human cognitive functions by realizing them with the robots. Humans are so complicated and it is difficult to mimic the well-developed human by robotic technologies. Therefore, it is necessary to understand how humans develop the complicated functions during the developmental process. We may be able to develop infant functions and make them evolve by tracing the human developmental process. This new study requires robot platforms that can mimic various aspects of the human developmental process. This paper introduces a series of robot platforms that we have developed for the studies with the synthetic approach.

Main advances in artificial intelligence robotics are algorithms, embodied in software on the level of application software. Low-level hardware programming, electronic, and mechanics are the necessary basis to enable the implementation of newly developed algorithms. Complex autonomous systems are challenged by the tasks that require fast reactions, resulting in high accelerations and forces. These systems, therefore, generally need low masses, stiff limbs, and a precise control.

To boost AI-research, more robotic systems that are appropriate to specific research questions are needed. Mechanical design is, therefore, faced with the task to provide specialized systems with a given amount of time and factors of production. This paper outlines an approach to increase the efficiency of engineering design in the field of robotics by analyzing the bilateral influence of the system concept with embodiment design driven by the state of the art small-batch manufacturing technologies.

The humanoid robotic system AILA is presented and the selected steps out of its design process are discussed. A way to clearly state the axioms and requirements that the developed system is based on is presented. The resulting dependencies lead to the embodiment design of the systems components, which are also influenced by the choice of suitable manufacturing technologies.

Biomechanics research shows that the ability of the human locomotor system depends on the functionality of a highly compliant motor system that enables a variety of different motions (such as walking and running) and control paradigms (such as flexible combination of feedforward and feedback controls strategies) and reliance on stabilizing properties of compliant gaits. As a new approach of transferring this knowledge into a humanoid robot, the design and implementation of the first of a planned series of biologically inspired, compliant, and musculoskeletal robots is presented in this paper. Its three-segmented legs are actuated by compliant mono- and biarticular structures, which mimic the main nine human leg muscle groups, by applying series elastic actuation consisting of cables and springs in combination with electrical actuators. By means of this platform, we aim to transfer versatile human locomotion abilities, namely running and later on walking, into one humanoid robot design. First experimental results for passive rebound, as well as push-off with active knee and ankle joints, and synchronous and alternate hopping are described and discussed. BioBiped1 will serve for further evaluation of the validity of biomechanical concepts for humanoid locomotion.

A novel metamorphic anthropomorphic hand is for the first time introduced in this paper. This robotic hand has a reconfigurable palm that generates changeable topology and augments dexterity and versatility of the hand. Structure design of the robotic hand is presented and based on mechanism decomposition kinematics of the metamorphic anthropomorphic hand is characterized with closed-form solutions leading to the workspace investigation of the robotic hand. With characteristic matrix equation, twisting motion of the metamorphic robotic hand is investigated to reveal both dexterity and manipulability of the metamorphic hand. Through a prototype, grasping and prehension of the robotic hand are tested to illustrate characteristics of the new metamorphic anthropomorphic hand.

This paper reports on the mechanical design of the huggable robot Probo. Its intentions include human–robot interaction (HRI), both physical and cognitive, with a special focus on children. Since most of the communication passes through nonverbal cues and since people rely on face-to-face communication, the focus of Probo's communicative skills lies initially on facial expressions. The robot has 20 high-precision motors in its head and body. They are used to actuate the ears, eyebrows, eyelids, eyes, trunk, mouth, and neck. To build safety aspects intrinsically in the robot's hardware, all the motors are linked with flexible components. In case of a collision, the robot will be elastic and safety will be ensured. The mechanics of Probo are covered by protecting plastic shells, foam, and soft fur. This gives Probo's animal-like look and makes the robot huggable.

This paper discusses a control architecture to equip humanoid robots with dynamic manipulation skills. Such skills are beneficial, as they increase the dexterity of humanoid robots and improve their handling of unforeseen situations. The nature of manipulation poses challenges with respect to environment perception, action planning, and motion control. These challenges are addressed in the paper: a dynamic force/torque (F/T) observer is discussed to reconstruct the environment F/Ts and to improve the interaction control. A method for online motion planning is investigated, which generates trajectories based on different selection criteria. These elements are integrated in a control design for dynamic manipulation and experimentally validated for two tasks: two-handed ball throwing and one-handed ball catching. Based on the experimental results, a modified end effector design with intrinsic compliance is proposed to improve the system performance that is demonstrated in case studies.

It is expected that the humanoid robots of the near future will "live" and work in a common environment with humans, which imposes the requirement that their operative efficiency ought to be close to that of humans. The main prerequisite to achieve this is to ensure the robot's efficient motion, which is its ability to compensate for the ever-present disturbances. The work considers the different strategies of how to compensate for the large disturbances that jeopardize the robot's dynamic balance in a most direct way, as well as the requirements to be met in the control synthesis. The ways in which such compensation can be efficiently realized are proposed and then verified by simulation.

We present a learning algorithm to determine the appropriate approaching pose to grasp a novel object. Our method focuses on the computation of valid end-effector orientations in order to make contact with the object at a given point. The system achieves this goal by generalizing from positive examples provided by a human operator during an offline training session. The technique is feature-based since it extracts salient attributes of the object to be grasped rather than relying on the availability of models or trying to build one. To compute the desired orientation, the robot performs three steps at run time. Using a multi-class Support Vector Machine (SVM), it first classifies the novel object into one of the object classes defined during training. Next, it determines its orientation, and, finally, based on the classification and orientation, it extracts the most similar example from the training data and uses it to grasp the object. The method has been implemented on a full-scale humanoid robotic torso equipped with multi-fingered hands and extensive results corroborate both its effectiveness and real-time performance.

During interpersonal interaction, common ground of our experiences takes an important role to facilitate mutual understanding as well as efficient communication. We introduce the concept of common ground, which has been an important issue in psychology, for developing robotic systems. With the conceptualization of the common ground among human, robot, and environmental objects, a comparative study is carried out between Human Human Interaction (HHI) and Human Robot Interaction (HRI), using paired groups with different expertise in "questioning and answering tasks." For comparison with HHI, the performance of a robot in the task was determined by both its own expertise as well that of its human partner. This indicates that the performance of the robotic system depends on the common ground shared with the human partners, and implies that a robotic system is required not only to be intelligently smart but also to be communicatively smart.