Research on Anthropomorphic Obstacle Avoidance Trajectory Planning for Adaptive Driving Scenarios Based on Inverse Reinforcement Learning Theory

The forward design of trajectory planning strategies requires preset trajectory optimization functions,resulting in poor adaptability of the strategy and an inability to accurately generate obstacle avoidance trajectories that conform to real driver behavior habits.In addition,owing to the strong time-varying dynamic characteristics of obstacle avoidance scenarios,it is necessary to design numerous trajectory optimization functions and adjust the corresponding parameters.Therefore,an anthropomorphic obstacle-avoidance trajectory planning strategy for adaptive driving scenarios is proposed.First,numerous expert-demonstrated trajectories are extracted from the HighD natural driving dataset.Subsequently,a trajectory expectation feature-matching algorithm is proposed that uses maximum entropy inverse reinforcement learning theory to learn the extracted expert-demonstrated trajectories and achieve automatic acquisition of the optimization function of the expert-demonstrated trajectory.Furthermore,a mapping model is constructed by combining the key driving scenario information that affects vehicle obstacle avoidance with the weight of the optimization function,and an anthropomorphic obstacle avoidance trajectory planning strategy for adaptive driving scenarios is proposed.Finally,the proposed strategy is verified based on real driving scenarios.The results show that the strategy can adjust the weight distribution of the trajectory optimization function in real time according to the“emergency degree”of obstacle avoidance and the state of the vehicle.Moreover,this strategy can generate anthropomorphic trajectories that are similar to expert-demonstrated trajectories,effectively improving the adaptability and acceptability of trajectories in driving scenarios.

STUDIES ON MECHANICS PROBLEM OF DYNAMIC WALKING OF ANTHROPOMORPHIC BIPED ROBOTS

This paper deals with the mechanics problem of dynamic walking of anthropomorphic biped robots. Through analysing the mechanics system of this kind of robots in detail, the motion constraint equations are established, three mechanics laws describing the r

Method for Calculating Cartesian Coordinates of Operator’s Arm Joints for Anthropomorphic Manipulator Master⁃Slave Control Using Exoskeleton

The main goal of the work is to increase the accuracy of the anthropomorphic manipulator master⁃slave teleoperation by calculating the coordinates of the operator’s arm joints.The master device is an exoskeleton worn on the operator’s arm,and the slave device is an anthropomorphic manipulator.A method based on the solution of the forward kinematics and empirical simplifications is proposed in this paper.The position of the nodal points of the exoskeleton was calculated by solving the direct kinematics problem.The coordinates of the operator’s arm joints,which were rigidly connected to the exoskeleton nodal points,were calculated geometrically.For the operator’s arm elbow joint,which was flexibly connected to the exoskeleton,an empirical relation was proposed.It simplified the calculation of the elbow joint position.The experiment showed a decrease in the mismatch between the operator’s arm angles and the manipulator joint angles from 20.7°to 2.9°.The proposed method increases the convenience of the master⁃slave control.

Anthropomorphic Classification of Tactile Qualities of Woven Fabrics Based on Skin/Textile Friction-Induced Vibrations

The common method classifying tactile qualities of fabrics is indirectly based on their difference of purely mechanical and physical properties. When human skin slides across fabric surfaces, the friction interaction between fabrics and skin will occur and trigger the cutaneouS tactile receptors, which are responsible for perceived tactile sensation. By the extracted features from friction- induced vibration signals, this paper presents an anthropomorphic classification method classifying tactile qualities of fabrics. The friction-induced vibration signals are recorded by a three-axis accelerator sensor, and the entice testing procedure is conducted in an anthropomorphic way to obtain vibration signals. The fast Fourier transform （FFT） is applied to analyzing the recoded signals, and then the classification features are extracted from the FFT data by the neurophysiological properties of tactile receptors. The extracted features are used to classify fabric samples by the softness sensation and the roughness sensation, respectively, and the classification performance is checked by a comparison with those in a sensory evaluation procedure. The results showed that the anthropomorphic objective classification method was precise and efficient to clarify tactile qualities of woven fabrics.

Study on a 7-DOF anthropomorphic weld arm

A kind of new obstacle space expression is proposed in this paper, in which a virtual force field (VFF) is built. Using the torque and joint optimization acted by the virtual force field on the anthropomorphic weld arm, the real-time selection of a redundant join (R-joint) is done and its equivalent virtual torque is obtained, thus the redundant joint can be controlled with whose force feedback. An inverse kinematics solution of a 6-DOF robot is applied to other six joints of the arm. Simulation experiments indicate the new inverse kinematics solution has perfect collision avoidance effect, and it is well simplified. Therefore, it can be applied to a welding task in complex operation space.

Hybrid Offset Slider Crank Mechanism for Anthropomorphic Flexion in Prosthetic Hands

The underactuated fingers used in prosthetic hands account for a large part of design consideration in anthropomorphic prosthetic hand design.There are considerable numbers of designs available for underactuated prosthetic fingers in literature but,emulating the anthropomorphic flexion movement is still a challenge due to the complex nature of the motion.To address this challenge,a hybrid mechanism using both linkage-based mechanism and tendon-driven actuation has been proposed in this paper.The presented mechanism includes a novel offset slider-crank-based finger that has been designed using a combination of different lengths of cranks and connecting rods.The prototypes of both the new mechanism and the conventional tendon-driven mechanism are constructed and compared experimentally based on interphalangeal joint angle trajectory during flexion.The angles achieved through the new hybrid mechanism are compared with the conventional tendon-driven mechanism and the Root Mean Square Error(RMSE)values have been calculated by comparing to the anthropomorphic flexion angles of the published literature.The RMSE values calculated for three interphalangeal joints of the hybrid mechanism are found to be less than their counter-parts of the conventional tendon-driven mechanism.In addition to achieving resemblance to anthropomorphic flexion angles,the mechanism is designed within the anthropometric human finger dimensions.

Anthropomorphic Design of the Human-Like Walking Robot

In this paper, we present a new concept of the mechanical design of a humanoid robot. The goal is to build a humanoid robot utilizing a new structure which is more suitable for human-like walking with the characteristics of the knee stretch, heel-contact, and toe-off. Inspired by human skeleton, we made an anthropomorphic pelvis for the humanoid robot. In comparison with con- ventional humanoid robots, with such the anthropomorphic pelvis, our robot is capable of adjusting the center of gravity of the upper body by the motion of pelvic tilt, thus reducing the required torque at the ankle joint and the velocity variations in hu- man-like walking. With more precise analysis of the foot mechanism, the fixed-length inverted pendulum can be used to describe the dynamics of biped walking, thus preventing redundant works and power consumption in length variable inverted pendulum system. As the result of the new structure we propose, a humanoid robot is able to walk with human-like gait.

On Adaptive Grasp with Underactuated Anthropomorphic Hands

To automatically adapt to the shape of different objects with enough grasping force is a challenge in the design of under- actuated anthropomorphic hands, because the grasped object is easily ejected from the hands during underactuated grasping process. The goal of this paper is to develop a design method of underactuated anthropomorphic hands to guarantee reliable adaption to different grasped objects. An analysis method is developed to investigate the evolution of motion and force in the whole underactuated grasping process. Based on the evolution of motion and force, the underactuated grasping process is decomposed into four aspects including initial contact state, grasp terminal state, grasp trajectory and rate of progress. More- over, the influence factors of such four aspects are found as the form of the combinations of underactuated mechanism pa- rameters. According to the four aspects of the underactuated grasping process, this paper presents a stepwise parameter design method through optimization of parameter combinations step-by-step. The reliable adaptive grasp for a wide scale of grasped object size is achieved. Experimental setups are constructed to corroborate the results from the theory analysis and design.

Design and Myoelectric Control of an Anthropomorphic Prosthetic Hand

This paper presents an anthropomorphic prosthetic hand using flexure hinges, which is controlled by the surface electromyography （sEMG） signals from 2 electrodes only. The prosthetic hand has compact structure with 5 fingers and 4 Degree of Freedoms （DoFs） driven by 4 independent actuators. Helical springs are used as elastic joints and the joints of each finger are coupled by tendons. The myoelectric control system which can classify 8 prehensile hand gestures is built. Pattern recognition is employed where Mean Absolute Value （MAV）, Variance （VAR）, the fourth-order Autoregressive （AR） coefficient and Sample Entropy （SE） are chosen as the optimal feature set and Linear Discriminant Analysis （LDA） is utilized to reduce the dimension. A decision of hand gestures is generated by LDA classifier after the current projected feature set and the previous one are ＂pre-smoothed＂, and then the final decision is obtained when the current decision and previous decisions are ＂post-smoothed＂ from the decisions flow. The prosthetic hand can perform prehensile postures for activities of daily living and carry objects under the control of EMG signals.

Design,Fabrication and Experiments of an Anthropomorphic Finger with Combined Compliant Joints

Fingers are the basic components of anthropomorphic hands.At present,most anthropomorphic fingers utilize rigid joints,which have obvious fabrication and assembly complexities as well as limited flexibility and adaptability.Thus,some anthropomorphic fingers were attempted to utilize compliant joints learned from bioinspiration,but they have a limited self-resetting ability and lateral deformation resistance,as well as occupying a large space and having a non-anthropomorphic appearance.In this paper,nine compliant joints for anthropomorphic fingers were analyzed using Finite Element Analysis(FEA),based on which two combined compliant joints were proposed,and the optimal one was obtained through FEA and experiments.An anthropomorphic finger that embeds parts of the compliant joint into the adjacent phalanxes was then designed.Finally,the anthropomorphic finger was fabricated and experiments were conducted.Experimental results show that the anthropomorphic finger with the proposed combined compliant joints has a better self-resetting ability and lateral deformation resistance while ensuring a large range of motion similar to that of the human finger,and the required actuating force is reasonable.Furthermore,the embedded joint structure can reduce the occupied space of the joint so as to improve the anthropomorphic appearance of the finger,and enhance its lateral deformation resistance.

An anthropomorphic controlled hand prosthesis system

Based on HIT/DLR(Harbin Institute of Technology/Deutsches Zentrum für Luft-und Raumfahrt) Prosthetic Hand II,an anthropomorphic controller is developed to help the amputees use and perceive the prosthetic hands more like people with normal physiological hands.The core of the anthropomorphic controller is a hierarchical control system.It is composed of a top controller and a low level controller.The top controller has been designed both to interpret the amputee's intensions through electromyography(EMG) signals recognition and to provide the subject-prosthesis interface control with electro-cutaneous sensory feedback(ESF),while the low level controller is responsible for grasp stability.The control strategies include the EMG control strategy,EMG and ESF closed loop control strategy,and voice control strategy.Through EMG signal recognition,10 types of hand postures are recognized based on support vector machine(SVM).An anthropomorphic closed loop system is constructed to include the customer,sensory feedback system,EMG control system,and the prosthetic hand,so as to help the amputee perform a more successful EMG grasp.Experimental results suggest that the anthropomorphic controller can be used for multi-posture recognition,and that grasp with ESF is a cognitive dual process with visual and sensory feedback.This process while outperforming the visual feedback process provides the concept of grasp force magnitude during manipulation of objects.

Anthropomorphic hand based on twisted-string-driven da Vinci’s mechanism for approaching human dexterity and power of grasp

Designing anthropomorphic prosthetic hands that approach human-level performance remains a great challenge.Commercial prosthetics are still inferior to human hands in several important properties, such as weight, size, fingertip force,grasp velocity, and active and passive dexterities. We present a novel design based on the under-actuated da Vinci’s mechanism driven by a flexible twisted string actuator(TSA). The distributed drive scheme allows structural optimization using a motion capture database to reproduce the natural movement of human hands while keeping adaptability to free-form objects. The application of TSA realizes a high conversion from motor torque to tendon contraction force while keeping the structure light,flexible, and compact. Our anthropomorphic prosthetic hand, consisting of six active and 15 passive degrees of freedom, has a weight of 280 g, approximately 70% of that of a human hand. It passed 30 of the 33 Feix grasp tests on objects in daily living and retained a loading capacity of 5 kg. This simple but intelligent mechanism leads to excellent stability and adaptability and renders feasible wide applications in prosthetics and in service robots.

A Synthetic Framework for Evaluating and Designing an Anthropomorphic Prosthetic Hand

The mimic of aesthetics, fianction, and rehabilitation application makes the prosthetic hand design an interdisciplinary, synthetic work. Prosthetic hands should be designed in a comprehensive consideration with a synthetic framework from multiple areas. In this case, a synthetic framework containing 12 anthropomorphism indexes is established and utilized to understand the human hand characteristic and quantifiably evaluate the anthropomorphism of a prosthetic hand. Our quantified evaluation results show that a Global Anthropomorphic Score （GAS） of the current commercial prosthetic hands is only 45.2%. The compliance, coupling speed ratio and configuration of the Degrees Of Freedom （DOF） are found to be the lowest three anthropomorphism evaluation indexes in all 12 indexes. In addition, a design priority is proposed based on the quantified evaluation results and contributes to a prosthetic hand design. Moreover, our correlation analysis results between each index and GAS show that, compared with the conventional evaluation index-grasp gesture, the rotation axis distribution index has a stronger distinguishing capability to the hand performance. Finally, a flowchart of prosthetic hand design was presented for a designer to design a prosthetic hand with a high anthropomorphism.

Investigating the customer trust in artificial intelligence: The role of anthropomorphism, empathy response, and interaction

Artificial intelligence(AI)applications are observed in different industries including the services,where the impressive changing pace is boosted by the technological advances in AI.The use of AI in the daily work of individuals and in shaping the relationship between firms and customers has resulted in increased efficiency and a higher degree of fascination in interaction.There are,however,customers'fears related to the use of AI.Therefore,understanding how AI affects customer trust is worth investigating.This study focuses on the AI applications and their impact on communication quality and customer trust.The features of AI applications investigated in this study include anthropomorphism,empathy response and interaction.A model was first empirically validated through Confirmatory Factor Analysis and tested using Covariance-Based Structural Equation Modelling.Data were then collected from a survey of 507 customers of two banks and two big telecommunication firms in Vietnam.Empirical results indicate that anthropomorphism and interaction do not play critical roles in generating customer trust in AI unless they create communication quality with customers.The ability of empathy response makes customers trust in various service situations.AI application seems to be a good solution for service firms to enhance their relationship with customers in difficult circumstances,including a pandemic crisis.This study delivers implications for enhancing AI adoption in the service firms that intend to innovate their future operations.

A Self-sensing TSA-actuated Anthropomorphic Robot Hand

This paper introduces a self-sensing anthropomorphic robot hand driven by Twisted String Actuators(TSAs).The use of TSAs provides several advantages such as muscle-like structures,high transmission ratios,large output forces,high efficiency,compactness,inherent compliance,and the ability to transmit power over distances.However,conventional sensors used in TSA-actuated robotic hands increase stiffness,mass,volume,and complexity,making feedback control challenging.To address this issue,a novel self-sensing approach is proposed using strain-sensing string based on Conductive Polymer Composite(CPC).By measuring the resistance changes in the strain-sensing string,the bending angle of the robot hand's fingers can be estimated,enabling closed-loop control without external sensors.The developed self-sensing anthropomorphic robot hand comprises a 3D-printed structure with five fingers,a palm,five self-sensing TSAs,and a 3D-printed forearm.Experimental studies validate the self-sensing properties of the TSA and the anthropomorphic robot hand.Additionally,a real-time Virtual Reality(VR)monitoring system is implemented for visualizing and monitoring the robot hand's movements using its self-sensing capabilities.This research contributes valuable insights and advancements to the field of intelligent prosthetics and robotic end grippers.

Empirical Formalism for the Phantom Scatter Factor of Small Fields: Using Different Density Media

We present the Empirical Formula (EF) to calculate the phantom scatter factor, Sp, of small radiation fields under charge particle dis-equilibrium conditions. The Empirical Formula (EF) was verified by examining the calculated data with experimentally measured data utilizing the anthropomorphic phantom in twelve different combinations of beam entry and point location, where the value for Sp per tissue composition was within 3% in 8/12 cases, 5% in 1/12 cases, and 10% in 3/12 cases. Our results showed a good agreement with experimental data to less than 1% when the ion chamber was surrounded by the homogeneous tissue, whether lung, soft tissue, or bone. Indicating that the prediction of the equation is valid, and it can be reliably used for phantom scatter factor calculation for different homogeneous media under charge particle dis- equilibrium conditions.

Three-Dimensional Rotational Angiography in Congenital Heart Disease:Estimation of Radiation Exposure

Objectives: There is an increasing use of three-dimensional rotational angiography (3D-RA) during catheterization of congenital heart disease. Dose-area-product (DAP) measured by the angiography system and computed-tomography dose index (CTDI) do not appear practical for dose assessment. Hence, we performed real dose measurements in anthropomorphic phantoms. Methods: Three different anthropomorphic phantoms (10 kg, 19 kg and 73 kg bodyweight) equipped with thermoluminescent dosimeters (TLD) were used. We used a typical standard diagnostic program and a low-dose program. The effective dose (ED) was calculated according to the International Commission on Radiological Protection (ICRP) 103. The 3D distribution of radiation in the body was assessed. Results: ED for the male 10 kg phantom was 0.192 mSv in the diagnostic program and 0.050 mSv (male) in the low-dose program. The 19 kg phantom received an ED of 0.205 mSv (male) in the diagnostic program. In the low-dose program the ED reached 0.058 mSv (male). The male adult 73 kg phantom was exposed with an ED of 0.730 mSv in the diagnostic program and 0.282 mSv in the low-dose program. ED for the female phantoms was slightly higher for both acquisition-programs. Dose distribution was inhomogeneous with a dose maximum in the esophageal region behind the heart, whereas in the brain, intestine and gonads we found nearly no radiation. Conclusions: 3D-RA imaging in the interventional catheter laboratory is possible with an effective dose lower than 1 mSv. With its potential to reduce fluoroscopic time and the number of control angiographies in catheterization and intervention in complex anatomy, it can decrease the radiation dose.

Humanoid robot heads for human-robot interaction:A review

The humanoid robot head plays an important role in the emotional expression of human-robot interaction(HRI).They are emerging in industrial manufacturing,business reception,entertainment,teaching assistance,and tour guides.In recent years,significant progress has been made in the field of humanoid robots.Nevertheless,there is still a lack of humanoid robots that can interact with humans naturally and comfortably.This review comprises a comprehensive survey of state-of-the-art technologies for humanoid robot heads over the last three decades,which covers the aspects of mechanical structures,actuators and sensors,anthropomorphic behavior control,emotional expression,and human-robot interaction.Finally,the current challenges and possible future directions are discussed.

Performance Evaluation Method for Automated Driving System in Logical Scenario

With the continuous improvement of automated driving technology,how to evaluate the performance of an automated driving system is attracting more and more attention.Meanwhile,with the creation of scenario-based test methods,the traditional evaluation index based on a single test can no longer meet the requirements of high-level safety verification for automated driving system,and the performance evaluation of such a system in logical scenarios will be the mainstream.Based on the scenario-based test method and Turing test theory,a performance evaluation method for an automated driving system in the whole parameter space of a logical scenario is proposed.The logical scenario parameter space is partitioned according to the risk degree of concrete scenario,and the evaluation process in different zones are determined.Subsequently,the anthropo-morphic index in the safe zone and the collision-avoidance index in the danger zone are defined by comparing test results of human driving and ideal vehicle motion.Taking front vehicle low-speed and cut-out scenarios as examples,two automated driving algorithms are tested in the virtual environment,and the test results are evaluated both by the proposed method and by human observation.The results show that the results of the proposed method are consistent with the subjective feelings of humans;additionally,it can be applied to scenario-based tests and the verification process of an automated driving system.

Anthropomorphism Indexes of the Kinematic Chain for Artificial Hands

Anthropomorphic hands have received increasing research interest in the fields of robotics and prosthetics.But it is not yet clear how to evaluate their anthropomorphism.Similarity in the kinematic chain is essential to achieve both functionality and cosmesis.A few previous works have addressed the definition of anthropomorphism indexes,although they have some limitations in its definition.In this study,three different anthropomorphism indexes have been defined to compare the kinematic chain of artificial hands with that of the human hand.These indexes are based on the comparison of:(I)the parameters of the kinematic chain(dimensions,type of joints,orientations and ranges of motion),(2)the reachable workspace,and(3)common grasping postures.Five artificial hands with different degrees of anthropomorphism have been compared using the three Anthropomorphism Indexes of the Kinematic Chain(AIKC).The results show a high correlation between the first and third AIKC for the hands compared.The second AIKC presents much lower values than the other two,although they are higher for hands that combine abduction/adduction and flexion/extension movements in the kinematic chain of each finger.These indexes can be useful during the initial stage of designing artificial hands or evaluating their anthropomorphism.