陈嘉浩

陈嘉浩  /  

  • 职  称: 副高级
  • 邮  编: 100190
  • 电子邮件: jiaohao.chen@ia.ac.cn
  • 部门/实验室: 多模态人工智能系统重点实验室
  • 通讯地址: 北京市海淀区中关村东路95号

个人简历

嘉浩,中国科学院自动化研究所副研究员,从事仿人肌肉骨骼机器人、脑启发式运动控制和强化学习领域的研究。搭建了仿人骨骼、关节结构和肌肉驱动方式的肌肉骨骼机械臂,针对仿人肌肉骨骼机械臂中存在的高冗余、强耦合和强非线性控制难点,研究并提出了一系列受人体运动皮层-小脑-脊髓-肌肉协同激活机制启发的运动控制,强化学习,sim2real,柔顺和灵巧操作,和多任务持续学习方法。

基于相关研究成果,近五年在IEEE TCYB、TSMCA、TMech、TASE、TCDS等国际SCI期刊上以第一/通讯作者发表论文11篇,发表位列本领域引用前1%的ESI高被引论文4篇(3篇第一作者),授权专利9项,相关成果获国内外院士、专家的广泛引用;主持国家自然科学基金青年科学项目,国家自然科学基金重大项目子课题,国家重点实验室青年基金等;获中国科学院优秀博士学位论文奖,北京市优秀博士学位论文提名奖,CAA-A类国际会议IEEE ICARM 2022机电一体化最佳论文(第一作者),中国自动化学会技术发明一等奖等;目前担任SCI国际期刊Robotic Intelligence and Automation的Editorial Assistant,中国自动化学会机器人智能专业委员会副秘书长,曾任IEEE Robotics and Automation Society学生活动委员会全球联合主席。

研究方向

肌肉骨骼机器人,脑启发式运动控制,强化学习,类脑智能机器人,持续学习

代表论著                                                                           

[1] Jiahao Chen, Hong Qiao. Muscle-synergies-based neuromuscular control for motion learning and generalization of a musculoskeletal system[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2021, 51(6): 3993-4006. ((ESI高被引论文)

[2] Jiahao Chen, Hong Qiao. Motor-cortex-like recurrent neural network and multitask learning for the control of musculoskeletal systems[J]. IEEE Transactions on Cognitive and Developmental Systems, 2022, 14(2): 424-436. (ESI高被引论文)

[3] Jiahao Chen, Yaxiong Wu, and Hong Qiao, Memory, attention, and muscle synergies based reinforcement and transfer learning for musculoskeletal robots under imperfect observation, IEEE/ASME Transactions on Mechatronics, 2024, doi:10.1109/TMECH.2024.3401045

[4] Jiahao Chen, Yaxiong Wu, Chaojing Yao, and Xiao Huang. Robust Motion Learning for Musculoskeletal Robots Based on a Recurrent Neural Network and Muscle Synergies, IEEE Transactions on Automation Science and Engineering, 2024, doi: 10.1109/TASE.2024.3379247

[5] Jiahao Chen, Ziyu Chen, Chaojing Yao, and Hong Qiao. Neural Manifold Modulated Continual Reinforcement Learning for Musculoskeletal Robots. IEEE Transactions on Cognitive and Developmental Systems, 2024, 16(1): 86-99. (ESI高被引论文)

[6] Jiahao Chen, Shanlin Zhong, Eerlong Kang, and Hong Qiao, Realizing human-like manipulation with a musculoskeletal system and biologically inspired control scheme[J]. Neurocomputing, vol. 339, pp. 116–129, Apr. 2019.

[7] Hong Qiao, Jiahao Chen*, Xiao Huang. A survey of brain-inspired intelligent robots with integration of vision, decision, motion control and musculoskeletal systems[J]. IEEE Transactions on Cybernetics, 2022, 52(10): 11267-11280. (通讯作者)

[8] Xiaona Wang, Jiahao Chen*, Hong Qiao*. Motion learning and Rapid Generalization for Musculoskeletal Systems based on Recurrent Neural Network Modulated by Initial States[J]. IEEE Transactions on Cognitive and Developmental Systems, 2022, 14(4): 1691-1704. (通讯作者)

[9] Xiaona Wang, Jiahao Chen*, and, Wei Wu. Motion Learning for Musculoskeletal Robots based on Cortex-Inspired Motor primitives and Modulation[J]. IEEE Transactions on Cognitive and Developmental Systems, 2024, 16(2): 744-756. (通讯作者)

[10] Wang, Xiaona, Jiahao Chen*, and Hong Qiao. A memory and attention-based reinforcement learning for musculoskeletal robots with prior knowledge of muscle synergies. Robotic Intelligence and Automation,2024, 44(2): 316-333. (通讯作者)

[11] Jiahao Chen, Xiao Huang, Xiaona Wang, Hong Qiao. Recurrent Neural Network based Partially Observed Feedback Control of Musculoskeletal Robots. 2022 International Conference on Advanced Robotics and Mechatronics (ICARM). IEEE, 2022.

[12] Shanlin Zhong, Jiahao Chen, Xinyu Niu, Hang Fu, Hong Qiao. Reducing redundancy of musculoskeletal robot with convex hull vertexes selection[J]. IEEE Transactions on Cognitive and Developmental Systems, 2020, 12(3): 601-617.

[13] Jinhan Zhang, Jiahao Chen, Wei Wu, and Hong Qiao. A Cerebellum-Inspired Prediction and Correction Model for Motion Control of a Musculoskeletal Robot[J]. IEEE Transactions on Cognitive and Developmental Systems, 2023, 15(3): 1209-1223.

[14] Jinhan Zhang, Jiahao Chen, Shanlin Zhong, and Hong Qiao. A Bio-Inspired Integration Model of Basal Ganglia and Cerebellum for Motion Learning of a Musculoskeletal Robot[J]. Journal of Systems Science and Complexity, 2024, 37(1): 82-113.

[15] Hong Qiao, Yaxiong Wu, Shanlin Zhong, Peijie Yin, and Jiahao Chen. Brain-inspired intelligent robotics: Theoretical analysis and systematic application[J]. Machine Intelligence Research, 2023, 20(1): 1-18.

专利成果                                                                          

[1] 陈嘉浩,乔红,钟汕林,吴伟,骨骼肌肉式机器人的肌肉控制和装配方法,发明专利, 201810218063.2,授权

[2] 陈嘉浩,乔红,基于脑启发多任务学习的肌肉骨骼机器人控制方法及系统,发明专利,202011286626.5,授权

[3] 陈嘉浩, 王萧娜, 乔红, 基于临界状态循环网络的肌肉骨骼机器人控制方法及装置, 发明专利,ZL202210476308.8,授权

[4] 张金涵,陈嘉浩,吴伟,乔红,基于小脑预测与修正的肌肉骨骼机器人控制方法及装置, 发明专利,ZL 2022 1 0418991.X,授权

[5] 周俊杰,陈嘉浩,邓虎,乔红,基于冗余肌肉骨骼系统的阶段式运动控制方法,发明专利, 201910807218.0,授权

[6] 乔红,吴伟,陈嘉浩,尹沛劼,一种类人机器人上肢运动模型的类神经精准控制方法, 201610101992.6,授权

[7] 钟汕林,乔红,陈嘉浩,类神经肌肉骨骼机器人上肢模型的简化方法,发明专利,201810144037.X,授权

[8] 范业锐,乔红,吴亚雄,原建博,陈嘉浩,非线性肌肉骨骼机器人控制方法、系统及设备,发明专利,ZL202110562679.3,授权

[9] 乔红,尹沛劼,吴伟,李川,陈嘉浩,一种类人机器人上肢运动的类神经控制方法,发明专利,201510960570.X,授权

获奖及荣誉                                                                          

2022年,获得中国科学院优秀博士学位论文奖

2022年,获得国际会议IEEE International Conference on Advanced Robotics & Mechatronics 2022 Best Paper Award in Mechatronics (第一作者)

2022年,获得北京市优秀博士学位论文提名奖

2018年,获得中国自动化学会技术发明一等奖,排名7

社会任职                                                                           

担任IEEE Robotics and Automation Society学生活动委员会全球联合主席,2019~2021

SCI国际期刊Robotic Intelligence and Automation的Editorial Assistant(编委会助理),2023~至今

SCI国际期刊Assembly Automation的Editorial Assistant(编委会助理),2021~2023

中国自动化学会机器人智能专业委员会的副秘书长,委员,2021~至今

中国自动化学会青年工作委员会,委员,2022~至今

承担科研项目情况                                                                   

(1)国家自然科学基金委员会, 青年科学基金项目, 面向肌肉骨骼机器人仿人操作的脑启发式运动学习,主持,30万

(2)国家自然科学基金委员会, 重大项目, 果蝇幼虫多模式软体运动控制的智能仿生计算模型,子课题负责人,127.6万