检索结果-南通市图书馆

A Unified Trajectory Optimization Approach for Long-Term and Reactive Motion Planning of Legged Locomotion

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2023年第5期20卷 2108-2122页

作者： Yapeng Shi Bin Yu Kaixian Ba mantian li School of Mechanical Engineering Yanshan UniversityNo.438 West Hebei AvenueQinhuangdao066004HebeiPeople’s Republic of China State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin150001People’s Republic of China

This paper proposes a unified trajectory optimization approach that simultaneously optimizes the trajectory of the center of mass and footholds for legged *** on a generic point-mass model,the approach is formulated as a nonlinear optimization problem,incorporating constraints such as robot kinematics,dynamics,ground reaction forces,obstacles,and target *** unified optimization approach can be applied to both long-term motion planning and the reactive online planning through the use of model predictive control,and it incorporates vector field guidance to converge to the long-term planned *** effectiveness of the approach is demonstrated through simulations and physical experiments,showing its ability to generate a variety of walking and jumping gaits,as well as transitions between them,and to perform reactive walking in obstructed environments.

关键词： Legged locomotion Motion planning Trajectory optimization Bionic robot

Squeezing More Past Knowledge for Online Class-Incremental Continual Learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2023年第3期10卷 722-736页

作者： Da Yu Mingyi Zhang mantian li Fusheng Zha Junge Zhang lining Sun Kaiqi Huang the State Key Laboratory of Robotics and System Harbin Institute of Technology(HIT)Harbin 150080China Center for Research on Intelligent System and Engineering Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190 School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Center for Research on Intelligent System and Engineering Institute of AutomationChinese Academy of Sciences(CASIA)Beijing 100190the School of Artificial IntelligenceUniversity of Chinese Academy of SciencesBeijing 100049 the CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai 200031China IEEE

Continual learning(CL)studies the problem of learning to accumulate knowledge over time from a stream of data.A crucial challenge is that neural networks suffer from performance degradation on previously seen data,known as catastrophic forgetting,due to allowing parameter *** this work,we consider a more practical online class-incremental CL setting,where the model learns new samples in an online manner and may continuously experience new ***,prior knowledge is unavailable during training and *** works usually explore sample usages from a single dimension,which ignores a lot of valuable supervisory *** better tackle the setting,we propose a novel replay-based CL method,which leverages multi-level representations produced by the intermediate process of training samples for replay and strengthens supervision to consolidate previous ***,besides the previous raw samples,we store the corresponding logits and features in the ***,to imitate the prediction of the past model,we construct extra constraints by leveraging multi-level information stored in the *** the same number of samples for replay,our method can use more past knowledge to prevent *** conduct extensive evaluations on several popular CL datasets,and experiments show that our method consistently outperforms state-of-the-art methods with various sizes of episodic *** further provide a detailed analysis of these results and demonstrate that our method is more viable in practical scenarios.

关键词： Catastrophic forgetting class-incremental learning continual learning(CL) experience replay

Robot Navigation Strategy in Complex Environment Based on Episode Cognition

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2023年第1期20卷 1-15页

作者： Jinsheng Yuan Wei Guo Zhiyuan Hou Fusheng Zha mantian li lining Sun Pengfei Wang State Key Laboratory of Robotics and System Harbin Institute of Technology(HIT)Harbin150001China Shenzhen Academy of Aerospace Technology Shenzhen518057China School of Mechanical and Electrical Engineering Lanzhou University of TechnologyLanzhou730050China

The hippocampal formation of the brain contains a series of nerve cells related to environmental cognition and *** cells can integrate their moment information and external perceptual information and acquire episodic cognitive *** episodic cognition and memory,organisms can achieve autonomous navigation in complex *** paper mainly studies the strategy of robot episode navigation in complex *** exploring the environment,the robot obtains subjective environmental cognition and forms a cognition *** grid cells information contained in the cognitive map can obtain the direction and distance of the target through vector calculation,which can get a shortcut through the inexperienced *** synaptic connection of place cells in the cognitive map can be used as the topological relationship between episode *** the target-oriented vector navigation encounters obstacles,the obstacles can be realized by setting closer *** on the known obstacle information obtained from boundary cells in the cognitive map,topological paths can be divided into multi-segment vector navigation to avoid encountering *** paper combines vector and topological navigation to achieve goal-oriented and robust navigation capability in a complex environment.

关键词： Bionic intelligent.Grid cell-Hippocampus-Navigation strategy Episode cognition

Analysis on the Performance of the SliP Runner with Nonlinear Spring Leg

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Mechanical Engineering 2013年第5期26卷 892-899页

作者： YU Haitao li mantian CAI Hegao State Key Laboratory of Robotics and System Harbin Institute of Technology

The spring-loaded inverted pendulum(SliP) has been widely studied in both animals and ***,the majority of the relevant theoretical studies deal with elastic leg,the linear leg length-force relationship of which is obviously conflict with the biological observations.A planar spring-mass model with a nonlinear spring leg is presented to explore the intrinsic mechanism of legged locomotion with elastic *** leg model is formulated via decoupling the stiffness coefficient and exponent of the leg compression in order that the unified stiffness can be scaled as convex,concave as well as linear *** apex return map of the SliP runner is established to investigate dynamical behavior of the fixed *** basin of attraction and Floquet Multiplier are introduced to evaluate the self-stability and initial state sensitivity of the SliP model with different stiffness *** numerical results show that larger stiffness exponent can increase top speed of stable running and also can enlarge the size of attraction domain of the fixed *** addition,the parameter variation is conducted to detect the effect of parameter dependency,and demonstrates that on the fixed energy level and stiffness profile,the faster running speed with larger convergence rate of the stable fixed point under small local perturbation can be achieved via decreasing the angle of attack and increasing the stiffness *** perturbation recovery test is implemented to judge the ability of the model resisting large external *** result shows that the convex stiffness performs best in enhancing the robustness of SliP runner negotiating irregular *** research sheds light on the running performance of the SliP runner with nonlinear leg spring from a theoretical perspective,and also guides the design and control of the bio-inspired legged robot.

关键词： spring-loaded inverted pendulum legged locomotion apex return map nonlinear spring

Approximate Perturbation Stance Map of the SliP Runner and Application to Locomotion Control

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2012年第4期9卷 411-422页

作者： Haitao Yu mantian li Pengfei Wang Hegao Cai State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150080P.R.China

This paper presents a novel method of perturbation to obtain the analytic approximate solution to the Spring-Loaded Inverted Pendulum （SliP） dynamics in stance phase with considering the effect of gravity. This perturbation solution achieves higher accuracy in predicting the apex state variables than the typical existing analytic approximations. Particularly, our solution is validated for non-symmetric trajectory of hopping in a large angle range. Furthermore, the stance controller of the SliP runner is developed to regulate the apex state based on the approximate apex return map. To compensate the energy variation between the current and desired apex states, a stiffness adjustment of the leg spring in stance phase is presented. The deadbeat controller of the angle of attack is designed to track the regulated apex height and velocity. The simulation demonstrates that the SliP runner applying the proposed stance controller reveals higher tracking accuracy and more rapidly converges to the regulated apex state.

关键词： legged locomotion spring-loaded inverted pendulum perturbation apex return map stiffness adjustment

CPG Control for Biped Hopping Robot in Unpredictable Environment

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2012年第1期9卷 29-38页

作者： Tingting Wang Wei Guo mantian li Fusheng Zha lining Sun State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150080P.R.China

A CPG control mechanism is proposed for hopping motion control of biped robot in unpredictable environment. Based on analysis of robot motion and biological observation of animal＇s control mechanism, the motion control task is divided into two simple parts： motion sequence control and output force control. Inspired by a two-level CPG model, a two-level CPG control mechanism is constructed to coordinate the drivers of robot joint, while various feedback information are introduced into the control mechanism. Interneurons within the control mechanism are modeled to generate motion rhythm and pattern promptly for motion sequence control; motoneurons are modeled to control output forces of joint drivers in real time according to feedbacks. The control system can perceive changes caused by unknown perturbations and environment changes according to feedback information, and adapt to unpredictable environment by adjusting outputs of neurons. The control mechanism is applied to a biped hopping robot in unpredictable environment on simulation platform, and stable adaptive motions are obtained.

关键词： biped robot unpredictable environment hopping motion control bionic control CPG

Bio-Inspired Controller for a Robot Cheetah with a Neural Mechanism Controlling Leg Muscles

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2012年第3期9卷 282-293页

作者： Xin Wang mantian li Pengfei Wang Wei Guo lining Sun State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001P.R.China

The realization of a high-speed running robot is one of the most challenging problems in developing legged robots. The excellent performance of cheetahs provides inspiration for the control and mechanical design of such robots. This paper presents a three-dimensional model of a cheetah that predicts the locomotory behaviors of a running cheetah. Applying biological knowledge of the neural mechanism, we control the muscle flexion and extension during the stance phase, and control the positions of the joints in the flight phase via a PD controller to minimize complexity. The proposed control strategy is shown to achieve similar locomotion of a real cheetah. The simulation realizes good biological properties, such as the leg retraction, ground reaction force, and spring-like leg behavior. The stable bounding results show the promise of the controller in high-speed locomotion. The model can reach 2.7 m-s^-1 as the highest speed, and can accelerate from 0 to 1.5 m-s^-1 in one stride cycle. A mechanical structure based on this simulation is designed to demonstrate the control approach, and the most recently developed hindlimb controlled by the proposed controller is presented in swinging-leg experiments and jump-force experiments.

关键词： biomimetics biologically-inspired robots legged robots neural mechanism artificial pneumatic muscle

Force-controlled Compensation Scheme for P-Q Valve-controlled Asymmetric Cylinder used on Hydraulic Quadruped Robots

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2020年第6期17卷 1139-1151页

作者： Yapeng Shi mantian li Fusheng Zha lining Sun Wei Guo Cong Ma Zhibin li State Key Laboratory of Robotics and System Harbin Institue of TechnologyHarbin 150001China Shenzhen Academy of Aerospace Technology China Aerospace ScienceShenzhen 518057China School of Informatics The University of EdinburghEdinburgh EH89ABUnited Kingdom

Under the requirement of the force controller of hydraulic quadruped robots,the goal of this work is to accurately track the force commands at the level of the hydraulic drive *** main contribution focuses on the development of a force-controlled compensation scheme,which is specifically aimed at the key issues affecting the hydraulic quadrupedal *** this idea,based on a P-Q valve-controlled asymmetric cylinder,we first establish a mathematical model for the hydraulic drive unit force control *** the desired force commands,a force feed-forward algorithm is presented to improve the dynamic performance of the ***,we propose a disturbance compensation algorithm to reduce the influence induced by external disturbances due to foot-ground ***,combining with a variable gain PI controller,a series of experiments are implemented on a force control performance test platform to verify the proposed *** results demonstrate that the force-controlled compensation scheme has the ability to notably improve the force tracking accuracy,reduce the response time and redundant force.

关键词： hydraulic drive unit force tracking P-Q valve-controlled asymmetric cylinder hydraulic quadruped robot

Velocity Control of a Bounding Quadruped via Energy Control and Vestibular Reflexes

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Bionic Engineering 2014年第4期11卷 556-571页

作者： Xin Wang mantian li Wei Guo Pengfei Wang lining Sun State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin 150001 P. R. China Department of Advanced Robotics (Fondazione) Istituto Italiano di Tecnologia Genova 16163 Italy

In this paper a bio-inspired approach of velocity control for a quadruped robot running with a bounding gait on compliant legs is set up. The dynamic properties ofa sagittal plane model of the robot are investigated. By analyzing the stable fixed points based on Poincare map, we find that the energy change of the system is the main source for forward velocity adjustment. Based on the analysis of the dynamics model of the robot, a new simple linear running controller is proposed using the energy control idea, which requires minimal task level feedback and only controls both the leg torque and ending impact angle. On the other hand, the functions of mammalian vestibular reflexes are discussed, and a reflex map between forward velocity and the pitch movement is built through statistical regression analysis. Finally, a velocity controller based on energy control and vestibular reflexes is built, which has the same structure as the mammalian nervous mechanism for body posture control. The new con- troller allows the robot to run autonomously without any other auxiliary equipment and exhibits good speed adjustment capa- bility. A series simulations and experiments were set to show the good movement agility, and the feasibility and validity of the robot system.

关键词： legged robots biologically-inspired robots biomimetics energy control vestibular reflexes