Humanoid Robot Platform Research Articles

Experimental Study on Modifiable Walking Pattern Generation for Handling Infeasible Navigational Commands

To accommodate various navigational commands, a humanoid should be able to change its walking motion in real time. Using the modifiable walking pattern generation (MWPG) algorithm, a humanoid can handle dynamic walking commands by changing its walking period, step length, and direction independently. If the humanoid is given a command to perform an infeasible movement, the algorithm substitutes the infeasible command with a feasible one using binary search. The feasible navigational command is subsequently translated into the desired center-of-mass (CM) state. Every sample time CM reference is generated using a zero-moment-point (ZMP) variation scheme. Based on this algorithm, various complex walking patterns can be generated, including backward and sideways walking, without detailed consideration of the feasibility of the navigational commands. In a previous study, the effectiveness of the MWPG algorithm was verified by dynamic simulation. This paper presents experimental results obtained using the small-sized humanoid robot platform DARwIn-OP.

An Evolutionary Optimization Approach for Optimal Hopping of Humanoid Robots

This paper proposes an evolutionary optimization approach for optimal hopping of humanoid robots. In the proposed approach, the hopping trajectory is generated by a central pattern generator (CPG). The CPG is one of the biologically inspired approaches, and it generates rhythmic signals by using neural oscillators. During the hopping motion, the disturbance caused by the ground reaction forces is compensated for by utilizing the sensory feedback in the CPG. Posture control is essential for a stable hopping motion. A posture controller is utilized to maintain the balance of the humanoid robot while hopping. In addition, a compliance controller using a virtual spring-damper model is applied for stable landing. For optimal hopping, the optimization of the hopping motion is formulated as a minimization problem with equality constraints. To solve this problem, two-phase evolutionary programming is employed. The proposed approach is verified through computer simulations using a simulated model of the small-sized humanoid robot platform DARwIn-OP.

Geometric backtracking for combined task and motion planning in robotic systems

Planners for real robotic systems should not only reason about abstract actions, but also about aspects related to physical execution such as kinematics and geometry. We present an approach to hybrid task and motion planning, in which state-based forward-chaining task planning is tightly coupled with motion planning and other forms of geometric reasoning. Our approach is centered around the problem of geometric backtracking that arises in hybrid task and motion planning: in order to satisfy the geometric preconditions of the current action, a planner may need to reconsider geometric choices, such as grasps and poses, that were made for previous actions. Geometric backtracking is a necessary condition for completeness, but it may lead to a dramatic computational explosion due to the large size of the space of geometric states. We explore two avenues to deal with this issue: the use of heuristics based on different geometric conditions to guide the search, and the use of geometric constraints to prune the search space. We empirically evaluate these different approaches, and demonstrate that they improve the performance of hybrid task and motion planning. We demonstrate our hybrid planning approach in two domains: a real, humanoid robotic platform, the DLR Justin robot, performing object manipulation tasks; and a simulated autonomous forklift operating in a warehouse.

DARPA Robotics Grand Challenge Participation and Ski-Type Gait for Rough-Terrain Walking

ABSTRACT In this paper, we briefly introduce the history of the Defense Advanced Research Projects Agency (DARPA) Grand Challenge programs with particular focus on the 2012 Robotics Challenge. As members of team DRC-HUBO, we propose different approaches for the Rough-Terrain task, such as enlarged foot pedals and a transformation into quadruped walking. We also introduce a new gait for humanoid robot locomotion to improve stability performance, called the Ski-Type gait. We analyze the stability performance of this gait and use the stability margin to choose between two candidate step sequences, Crawl-1 and Crawl-2. Next, we perform a force/torque analysis for the redundant closed-chain system in the Ski-Type gait, and determine the joint torques by minimizing the total energy consumption. Based on the stability and force/torque analysis, we design a cane length to support a feasible and stable Crawl-2 gait on the HUBO2 humanoid robot platform. Finally, we compare our experimental results with biped walking to validate the Ski-Type gait. We also present our team performance in the trials of the Robotics Challenge.

Embedding inference engine in fuzzy expert robotic system shell in a humanoid robot platform for selecting stochastic appropriate fuzzy implications for approximate reasoning

The purpose of this research is to select an appropriate fuzzy implication for approximate reasoning under each situation and to solve reasoning based on fuzzy production rules, which is usually referred to as approximate reasoning in the design of inference engines for fuzzy expert systems, Predicting the knowledge domain is removed from an expert system, the remaining structure is to extract an expert system shell, Here the applicability of an expert system shell is not necessarily restricted to one particular knowledge domain. An inference engine embedded in an appropriate expert system shell is made reusable for different domains of knowledge for different expert systems, with relevant human experts. In this research we identified meaningful criteria in terms of which distinct fuzzy implications could be evaluated and compared. In this research the explanatory interface facilitates communication between the user and the expert system. Approaches to evaluation are done for the relevant production rules by modus ponens. In this research it has been observed that experienced results are able to perform and recognized that the areas of fuzzy systems and neural networks are strongly interconnected, Here in this research neural networks have been proven that fuzzification is very useful in this humanoid robotic research using fuzzy set for constructing membership functions of relevant fuzzy sets and other context-dependent entities from sample data. We had explored here that the motivation for approximating fuzzy systems by neural networks is based upon the inherent capability of neural networks to perform this massive parallel processing of information. This is relevant to fuzzy controllers and more for fuzzy expert systems that processed large numbers of fuzzy inference rules in this real-time research.

PSO를 이용한 휴머노이드 로봇의 최적자세 생성

Humanoid robot is the most suitable robot platform for effective human and robot interaction. However, the robot`s complicated body structure containing more than twenty joint actuators makes it difficult to generate stable and elaborate postures using the conventional inverse kinematic method. This paper proposes an alternative approach to generate difficult postures of touching an object placed in front of the foot by the left or right hand with its torso bent forward in single support phase using the fast computational optimization method, particle swarm optimization. The simulated postures are also applied to a commercial humanoid robot platform, which validates the feasibility of the proposed approach.

Humanoid robot arm performance optimization using multi objective evolutionary algorithm

As humanoid robots are expected to operate in human environments they are expected to perform a wide range of tasks. Therefore, the robot arm motion must be generated based on the specific task. In this paper we propose an optimal arm motion generation satisfying multiple criteria. In our method, we evolved neural controllers that generate the humanoid robot arm motion satisfying three different criteria; minimum time, minimum distance and minimum acceleration. The robot hand is required to move from the initial to the final goal position. In order to compare the performance, single objective GA is also considered as an optimization tool. Selected neural controllers from the Pareto solution are implemented and their performance is evaluated. Experimental investigation shows that the evolved neural controllers performed well in the real hardware of the mobile humanoid robot platform.

휴머노이드 로봇의 전방향 이족보행 원격제어를 위한 안드로이드 애플리케이션 개발

Abstract: Humanoid robot is the most suitable robot platform for effective human interaction and various intelligent services. The present work addresses development of real time wireless control application of humanoid robot’s forward and backward walks, and turning in walking. For convenience of human users, the application is developed on Android OS (Operating System) working on his or her smartphone. To this end, theoretic background on various-directional biped walking is proposed based on joint trajectories for forward walking, which have been shaped with a global optimization method. In this paper, backward walking is scheduled by interchange of angles and angular velocities and additional change of signs in angular velocities at all the via-points connecting cubic polynomial trajectories. Turning direction in walking is also implemented by activating the transversal hip joint initially located in the support leg in two stages. After validation of the proposed walking schemes with Matlab simulator, a smartphone application for the omnidirectional walking has been developed to control a humanoid robot platform named DARwIn-OP interconnected via Wi-Fi. Experiment result of the present wireless control of a humanoid robot with smartphone is successful, and the application will be released in application market near future. Keywords: android application, biped walking, humanoid robot, wireless control, direction turning

Modeling and design of a humanoid robotic face based on an active drive points model

This study develops a face robot with human-like appearance for making facial expressions similar to a specific subject. First, an active drive points (ADPs) model is proposed for establishing a robotic face with less active degree of freedom for bipedal humanoid robots. Then, a robotic face design method is proposed, with the robot possessing similar facial appearance and expressions to that of a human subject. A similarity evaluation method is presented to evaluate the similarity of facial expressions between a robot and a specific human subject. Finally, the proposed facial model and the design methods are verified and implemented on a humanoid robot platform.

Design and Development of the Humanoid Robot BHR-5

This paper presents the mechanical and control system design of the latest humanoid robot platform, BHR-5, from Beijing Institute of Technology. The robot was developed as a comprehensive platform to investigate the planning and control for the fast responsive motion under unforeseen circumstances, for example, playing table-tennis. It has improvement on mechanical structure, stiffness, and reliability. An open control architecture based on concurrent multichannel communication mode of CAN bus is proposed to upgrade the real-time communication performance and the expansibility of the control system. Experiments on walking and playing table-tennis validate the effectiveness of the design.

Pilot clinical application of an adaptive robotic system for young children with autism.

It has been argued that clinical applications of advanced technology may hold promise for addressing impairments associated with autism spectrum disorders. This pilot feasibility study evaluated the application of a novel adaptive robot-mediated system capable of both administering and automatically adjusting joint attention prompts to a small group of preschool children with autism spectrum disorders (n = 6) and a control group (n = 6). Children in both groups spent more time looking at the humanoid robot and were able to achieve a high level of accuracy across trials. However, across groups, children required higher levels of prompting to successfully orient within robot-administered trials. The results highlight both the potential benefits of closed-loop adaptive robotic systems as well as current limitations of existing humanoid-robotic platforms.

Can Robotic Interaction Improve Joint Attention Skills?

Although it has often been argued that clinical applications of advanced technology may hold promise for addressing impairments associated with autism spectrum disorder (ASD), relatively few investigations have indexed the impact of intervention and feedback approaches. This pilot study investigated the application of a novel robotic interaction system capable of administering and adjusting joint attention prompts to a small group (n = 6) of children with ASD. Across a series of four sessions, children improved in their ability to orient to prompts administered by the robotic system and continued to display strong attention toward the humanoid robot over time. The results highlight both potential benefits of robotic systems for directed intervention approaches as well as potent limitations of existing humanoid robotic platforms.

Signal Processing and Application of Six-axis Force/Torque Sensor Integrated in Humanoid Robot Foot

Six-axis force/torque sensor (F/T sensor) that can detect three orthogonal forces and torques has been extensively adopted in humanoid robot foot for stable control. Due to the F/T sensors being seriously influenced by the electromagnetic interference from ankle generator, signal stability of F/T sensor is still one of the main influencing factors for accurately dynamical and stable control. Though the problem with influencing electromagnetic noise can be solved generally and partially by shielding of the sensor and wires, this traditional method will to some extend face implementation difficulty induced by special mounting space and application environment especially in humanoid robot ankle. Therefore, the research on the output signal stability and precision of the F/T sensors has still been one of the most essential subjects for humanoid robot dynamic equilibrium control. In this paper, some various signal processing methods have been adopted and analyzed comparatively with the aim at the output signal anti-interference processing of F/T sensors. And the filtering effect and its feasibility were verified experimentally in the dynamic walking motion of humanoid robot platform BHR-2.

Modular Design Concept of a Humanoid Robot Platform

Most of the biped robots or humanoid robots developed so far have been designed with serialactuated mechanism. the ratio between power and weight has not been very good. Some abilities of the humanoid robot are dependent on the weakest motor just like the cannikin law. Most of the human joints are not serial-actuated but parallel-actuated except the knee joint which is a one DOF joint. In the study, two kinds of module are put forward: basic module and composite module, and the configurations of the joints and limbs are designed by these modules. Based on logic diagram, many kinds of the humanoid robot are structured with these joints and limbs. As an applicable example, the humanoid robot SJTU-HR1 is presented.

Perception of effective contact area distribution for humanoid robot foot

Maintaining dynamical stability for humanoid robots to walk or run in even environments has so far been achieved. However, it will become a challenge work to keep balance under rough terrains, because the effective contact area (ECA) between the feet and the uneven environments is less than that on even ground. Thus some control schemes are additionally needed for robot to keep dynamical balance, which increases the complexity of control. In view of that, flexible force sensor array (FFSA) system is adopted under robot feet to detect the ECA in the case of stepping on rough terrains. Structure optimum, data acquisition, processing methods, etc., of the FFSA system are all elaborately provided in this paper. And the feasibility and validity of the FFSA system mounted in the robot foot system are experimentally tested on the humanoid robot platform BHR-2.

Intelligent facial emotion recognition and semantic-based topic detection for a humanoid robot

Automatic perception of human affective behaviour from facial expressions and recognition of intentions and social goals from dialogue contexts would greatly enhance natural human robot interaction. This research concentrates on intelligent neural network based facial emotion recognition and Latent Semantic Analysis based topic detection for a humanoid robot. The work has first of all incorporated Facial Action Coding System describing physical cues and anatomical knowledge of facial behaviour for the detection of neutral and six basic emotions from real-time posed facial expressions. Feedforward neural networks (NN) are used to respectively implement both upper and lower facial Action Units (AU) analysers to recognise six upper and 11 lower facial actions including Inner and Outer Brow Raiser, Lid Tightener, Lip Corner Puller, Upper Lip Raiser, Nose Wrinkler, Mouth Stretch etc. An artificial neural network based facial emotion recogniser is subsequently used to accept the derived 17 Action Units as inputs to decode neutral and six basic emotions from facial expressions. Moreover, in order to advise the robot to make appropriate responses based on the detected affective facial behaviours, Latent Semantic Analysis is used to focus on underlying semantic structures of the data and go beyond linguistic restrictions to identify topics embedded in the users’ conversations. The overall development is integrated with a modern humanoid robot platform under its Linux C++ SDKs. The work presented here shows great potential in developing personalised intelligent agents/robots with emotion and social intelligence.

ヒト型汎用ロボットによるライフサイエンスの近代化

ヒト型汎用ロボットによるライフサイエンスの近代化

Comparing the effect of humanoid and human face for the spatial orientation of attention

The current study was designed to investigate how the automatic spatial orientation of attention induced by the perception of another agent's orientation of attention is modulated by the social nature of the other agent. Modified versions of the Posner task, using a real or schematic face with eyes or head looking toward the left or the right before a to-be-detected target appears on one side of the screen have been used to demonstrate a reduction of reaction time (RT) for target detection when the gaze is directed toward the target, even though the cue is not informative. We compared the effect of two agents, the humanoid robotic platform Nao and a real human, using head turn to cue the spatial orientation of attention. Our results reproduced the typical Posner effect, with reduced RT to valid compared to invalid spatial cues. RT increased when no spatial information was provided, interpreted as an increased difficulty to disengage from a direct gaze. RT was also increased when the robot was used instead of the human face and when the eyes of the stimuli were blacked out. Both effects were interpreted as resulting from an increased difficulty to disengage attention from the central stimulus because of its novelty. In all experiments, there was no interaction between cue validity and cue agent, implying that the exact nature of the human-like agent didn't have an effect on the automatic spatial orientation of attention. Altogether, our results imply that a humanoid face is as potent as a human face to trigger an automatic orientation of spatial attention.

THE DESIGN OF THE iCub HUMANOID ROBOT

This article describes the hardware design of the iCub humanoid robot. The iCub is an open-source humanoid robotic platform designed explicitly to support research in embodied cognition. This paper covers the mechanical and electronic design of the first release of the robot. A series upgrades developed for the second version of the robot (iCub2), which are aimed at the improvement of the mechanical and sensing performance, are also described.

Predictive coding strategies for developmental neurorobotics.

In recent years, predictive coding strategies have been proposed as a possible means by which the brain might make sense of the truly overwhelming amount of sensory data available to the brain at any given moment of time. Instead of the raw data, the brain is hypothesized to guide its actions by assigning causal beliefs to the observed error between what it expects to happen and what actually happens. In this paper, we present a variety of developmental neurorobotics experiments in which minimalist prediction error-based encoding strategies are utilize to elucidate the emergence of infant-like behavior in humanoid robotic platforms. Our approaches will be first naively Piagian, then move onto more Vygotskian ideas. More specifically, we will investigate how simple forms of infant learning, such as motor sequence generation, object permanence, and imitation learning may arise if minimizing prediction errors are used as objective functions.