Passive bionic feet,known for their human-like compliance,have garnered attention for their potential to achieve notable environmental adaptability.In this paper,a method was proposed to unifying passive bionic feet s...Passive bionic feet,known for their human-like compliance,have garnered attention for their potential to achieve notable environmental adaptability.In this paper,a method was proposed to unifying passive bionic feet static supporting stability and dynamic terrain adaptability through the utilization of the Rigid-Elastic Hybrid(REH)dynamics model.First,a bionic foot model,named the Hinge Tension Elastic Complex(HTEC)model,was developed by extracting key features from human feet.Furthermore,the kinematics and REH dynamics of the HTEC model were established.Based on the foot dynamics,a nonlinear optimization method for stiffness matching(NOSM)was designed.Finally,the HTEC-based foot was constructed and applied onto BHR-B2 humanoid robot.The foot static stability is achieved.The enhanced adaptability is observed as the robot traverses square steel,lawn,and cobblestone terrains.Through proposed design method and structure,the mobility of the humanoid robot is improved.展开更多
With the increasing use of humanoid robots in several sectors of industrial automation and manufacturing, navigation and path planning of humanoids has emerged as one of the most promising area of research. In this pa...With the increasing use of humanoid robots in several sectors of industrial automation and manufacturing, navigation and path planning of humanoids has emerged as one of the most promising area of research. In this paper, a navigational controller has been developed for a humanoid by using fuzzy logic as an intelligent algorithm for avoiding the obstacles present in the environment and reach the desired target position safely. Here, the controller has been designed by careful consideration of the navigational parameters by the help of fuzzy rules. The sensory information regarding obstacle distances and bearing angle towards the target are considered as inputs to the controller and necessary velocities for avoiding the obstacles are obtained as outputs. The working of the controller has been tested on a NAO humanoid robot in V-REP simulation platform. To validate the simulation results, an experimental platform has been designed under laboratory conditions, and experimental analysis has been performed.Finally, the results obtained from both the environments are compared against each other with a good agreement between them.展开更多
A lower-part humanoid robot CHP-1 with 12 degree-of-freedom of motion has been developed for cooperative motion,such as pushing or lifting an object.The capability of the robot is mainly dependent on the performance o...A lower-part humanoid robot CHP-1 with 12 degree-of-freedom of motion has been developed for cooperative motion,such as pushing or lifting an object.The capability of the robot is mainly dependent on the performance of the motors,thus the motors need to be properly selected.For the purpose,the kinematics of the robot was analyzed,and a number of simulations for two kinds of cooperative motions were carried out.The torques required at each motor of the robot under external forces were obtained.Here,the external forces were also estimated through simulation and literature survey.On the basis of the torques found,the selection of motors was finally suggested,and the motors are to be installed to the humanoid robot.展开更多
In order to make the humanoid robot walk freely in complicated circumstance, the reliable capabilities for obtaining plane information from its surroundings are demanded. A system for extracting planes from data taken...In order to make the humanoid robot walk freely in complicated circumstance, the reliable capabilities for obtaining plane information from its surroundings are demanded. A system for extracting planes from data taken by stereo vision was presented, After the depth image was obtained, the pixels of each line were scanned and split into straight line segments. The neighbouring relation of line segments was kept in link structure. The groups of three line segments were selected as seed regions. A queue was maintained for storing seed regions, and then the plane region was expanded around the seed region. The process of region growing continued until the queue of seed regions was empty. After trimming, the edges of the planes became smooth. In the end, extracted planes were obtained. In the experiment, two models were used： pipe and stairs. Two planes in pipe mode/and six planes in stairs model were extracted exactly. The speed and precision of algorithm can satisfy the demands of humanoid robot＇s navigation.展开更多
A humanoid robot has high mobility but possibly risks of tipping over. Until now, onemain topic on humanoid robots is to study the walking stability; the issue of the running stabilityhas rarely been investigated. The...A humanoid robot has high mobility but possibly risks of tipping over. Until now, onemain topic on humanoid robots is to study the walking stability; the issue of the running stabilityhas rarely been investigated. The running is di?erent from the walking, and is more di?cult tomaintain its dynamic stability. The objective of this paper is to study the stability criterion forhumanoid running based on the whole dynamics. First, the cycle and the dynamics of running areanalyzed. Then, the stability criterion of humanoid running is presented. Finally, the e?ectivenessof the proposed stability criterion is illustrated by a dynamic simulation example using a dynamicanalysis and design system (DADS).展开更多
为解决人形机器人在单一策略模型下同时学习多样化全身运动技能时,不同技能过渡过程中动作完成质量与动作间连贯性难以兼顾的难题,提出了一种单模型多技能高效模仿学习(single model imitation learning for multi-skill efficiency,SMI...为解决人形机器人在单一策略模型下同时学习多样化全身运动技能时,不同技能过渡过程中动作完成质量与动作间连贯性难以兼顾的难题,提出了一种单模型多技能高效模仿学习(single model imitation learning for multi-skill efficiency,SMILE)方法.该方法结合目标条件强化学习与生成对抗模仿学习,实现高效的全身运动策略生成.通过在奖励函数中引入偏好奖励,引导策略兼顾不同技能间的动作特性差异,有效降低策略陷入次优解的风险;通过基于失败次数的优先采样方法,自适应提高策略表现较差样本的采样概率,进一步提升学习多样化技能的效率与性能.仿真结果表明,SMILE方法可使人形机器人掌握包括站立、深蹲、行走、跃坎、俯身详察、捡拾物体等多种类人全身技能,且能够在不同技能之间实现连贯的过渡,成功率达到93.33%.在消融实验中,去除偏好奖励或基于失败次数的优先采样方法后,成功率分别降至53.33%和73.33%,训练效率也明显降低.与基于目标条件强化学习的全身运动策略生成方法相比,SMILE方法缓解了多技能训练过程中原有技能遗忘或性能退化现象.SMILE方法有效缓解了不同技能特性差异导致策略优化存在的冲突,而且兼顾了技能间过渡动作质量与连贯性,为人形机器人多技能模仿学习提供了新思路.展开更多
基金supported by the National Natural Science Foundation of China(Grant No.62073041)the Open Fund of Laboratory of Aerospace Servo Actuation and Transmission(Grant No.LASAT-2023A04)the Fundamental Research Funds for the Central Universities(Grant Nos.2024CX06011,2024CX06079)。
文摘Passive bionic feet,known for their human-like compliance,have garnered attention for their potential to achieve notable environmental adaptability.In this paper,a method was proposed to unifying passive bionic feet static supporting stability and dynamic terrain adaptability through the utilization of the Rigid-Elastic Hybrid(REH)dynamics model.First,a bionic foot model,named the Hinge Tension Elastic Complex(HTEC)model,was developed by extracting key features from human feet.Furthermore,the kinematics and REH dynamics of the HTEC model were established.Based on the foot dynamics,a nonlinear optimization method for stiffness matching(NOSM)was designed.Finally,the HTEC-based foot was constructed and applied onto BHR-B2 humanoid robot.The foot static stability is achieved.The enhanced adaptability is observed as the robot traverses square steel,lawn,and cobblestone terrains.Through proposed design method and structure,the mobility of the humanoid robot is improved.
文摘With the increasing use of humanoid robots in several sectors of industrial automation and manufacturing, navigation and path planning of humanoids has emerged as one of the most promising area of research. In this paper, a navigational controller has been developed for a humanoid by using fuzzy logic as an intelligent algorithm for avoiding the obstacles present in the environment and reach the desired target position safely. Here, the controller has been designed by careful consideration of the navigational parameters by the help of fuzzy rules. The sensory information regarding obstacle distances and bearing angle towards the target are considered as inputs to the controller and necessary velocities for avoiding the obstacles are obtained as outputs. The working of the controller has been tested on a NAO humanoid robot in V-REP simulation platform. To validate the simulation results, an experimental platform has been designed under laboratory conditions, and experimental analysis has been performed.Finally, the results obtained from both the environments are compared against each other with a good agreement between them.
基金Project supported by the Second Stage of Brain Korea 21 Projects
文摘A lower-part humanoid robot CHP-1 with 12 degree-of-freedom of motion has been developed for cooperative motion,such as pushing or lifting an object.The capability of the robot is mainly dependent on the performance of the motors,thus the motors need to be properly selected.For the purpose,the kinematics of the robot was analyzed,and a number of simulations for two kinds of cooperative motions were carried out.The torques required at each motor of the robot under external forces were obtained.Here,the external forces were also estimated through simulation and literature survey.On the basis of the torques found,the selection of motors was finally suggested,and the motors are to be installed to the humanoid robot.
基金Project(60776816) supported by the National Natural Science Foundation of China and Civil Aviation Administration of ChinaProject(8251064101000005) supported by the Natural Science Foundation of Guangdong Province,China
文摘In order to make the humanoid robot walk freely in complicated circumstance, the reliable capabilities for obtaining plane information from its surroundings are demanded. A system for extracting planes from data taken by stereo vision was presented, After the depth image was obtained, the pixels of each line were scanned and split into straight line segments. The neighbouring relation of line segments was kept in link structure. The groups of three line segments were selected as seed regions. A queue was maintained for storing seed regions, and then the plane region was expanded around the seed region. The process of region growing continued until the queue of seed regions was empty. After trimming, the edges of the planes became smooth. In the end, extracted planes were obtained. In the experiment, two models were used： pipe and stairs. Two planes in pipe mode/and six planes in stairs model were extracted exactly. The speed and precision of algorithm can satisfy the demands of humanoid robot＇s navigation.
文摘A humanoid robot has high mobility but possibly risks of tipping over. Until now, onemain topic on humanoid robots is to study the walking stability; the issue of the running stabilityhas rarely been investigated. The running is di?erent from the walking, and is more di?cult tomaintain its dynamic stability. The objective of this paper is to study the stability criterion forhumanoid running based on the whole dynamics. First, the cycle and the dynamics of running areanalyzed. Then, the stability criterion of humanoid running is presented. Finally, the e?ectivenessof the proposed stability criterion is illustrated by a dynamic simulation example using a dynamicanalysis and design system (DADS).
文摘针对常见仿人机器人步态优化方法中存在模型复杂、数据量大和收敛速度慢的问题,采用投影解析法分析仿人机器人运动模型,利用三次样条插值法对步态轨迹进行规划,基于粒子群算法(Particle Swarm Optimization,PSO)优化仿人机器人关节电机的角度。将零力矩点(Zero Moment Point,ZMP)作为仿人机器人动态稳定的判断依据,并把最小轨迹变量和每步驱动能耗构造为目标函数。MATLAB仿真实验表明:所提方法在仿人机器人步态优化中具有高效地搜寻全局最优参数能力,使仿人机器人实现了轨迹平滑、控制稳定的初始步、周期步和终止步等。
文摘为解决人形机器人在单一策略模型下同时学习多样化全身运动技能时,不同技能过渡过程中动作完成质量与动作间连贯性难以兼顾的难题,提出了一种单模型多技能高效模仿学习(single model imitation learning for multi-skill efficiency,SMILE)方法.该方法结合目标条件强化学习与生成对抗模仿学习,实现高效的全身运动策略生成.通过在奖励函数中引入偏好奖励,引导策略兼顾不同技能间的动作特性差异,有效降低策略陷入次优解的风险;通过基于失败次数的优先采样方法,自适应提高策略表现较差样本的采样概率,进一步提升学习多样化技能的效率与性能.仿真结果表明,SMILE方法可使人形机器人掌握包括站立、深蹲、行走、跃坎、俯身详察、捡拾物体等多种类人全身技能,且能够在不同技能之间实现连贯的过渡,成功率达到93.33%.在消融实验中,去除偏好奖励或基于失败次数的优先采样方法后,成功率分别降至53.33%和73.33%,训练效率也明显降低.与基于目标条件强化学习的全身运动策略生成方法相比,SMILE方法缓解了多技能训练过程中原有技能遗忘或性能退化现象.SMILE方法有效缓解了不同技能特性差异导致策略优化存在的冲突,而且兼顾了技能间过渡动作质量与连贯性,为人形机器人多技能模仿学习提供了新思路.
