以下文章来源于信息与控制，欢迎转载，请全文转载并插入该公众号名片。
引用格式
任丹梅, 边飞飞. 机器人柔顺行为控制方法综述[J]. 信息与控制, 2024, 53(4): 433-452.
扫描二维码阅读全文
1
摘要
机器人柔顺行为是指机器人能够动态调整自身运动策略，从而对人或环境的物理交互表现出一定的顺从性。本文围绕机器人柔顺行为控制方法进行综述。首先依据不同的控制回路对柔顺控制方法进行了分类。然后分别对在运动控制回路的实现方法、在路径规划回路的实现方法和在任务调度回路的实现方法进行了整理，分析了每种方法赋予机器人的不同柔顺性特征。最后总结了机器人柔顺控制的几种典型应用，展望了机器人柔顺控制技术的未来趋势，以期为机器人柔顺控制研究提供新的思路和方向。
2
研究背景及主要内容
当前，机器人与人和环境之间进行安全、柔顺物理交互的需求愈发强烈，而柔顺性则是机器人为了应对这一物理交互需求所必需的重要特性。
机器人柔顺性是指当机器人与周围的人或者物体发生物理接触类型的交互作用时，能够利用视觉、力触觉、生物电信号等信息理解人的意图和感知环境的变化，并据此在任务调度、路径规划、运动控制等回路中动态调整机器人的运动策略，使得机器人对人或环境的交互表现出一定的顺从性。该定义包含了3个方面的内容，分别为意图检测(intent detection)、协作仲裁(arbitration)和状态反馈(state feedback)。意图检测是指对人的意图的理解和对环境的感知，该内容是机器人柔顺作业的基础技术，为柔顺作业提供决策依据；协作仲裁是指机器人和人对任务主导权的分配机制，一般通过动态调整机器人的运动策略实现，该内容是机器人柔顺作业的核心，决定了机器人与人或环境的真实交互状态和最终交互效果；状态反馈是指利用人和机器人之间的物理耦合通道，将机器人的作业状态反馈给人，该内容是实现机器人柔顺作业闭环的关键，给予人对交互状态的掌控权，保证柔顺作业稳定进行。
人机物理交互需求的增多和柔顺行为的诸多优良特性使得机器人柔顺行为控制逐渐成为研究热点。我国《“十四五”机器人产业发展规划》将人机自然交互技术纳入“机器人核心技术攻关行动”专栏中的前沿技术范畴。随后，为了落实发展规划中的内容，2023年1月，工业和信息化部等十七部门印发了《“机器人+”应用行动实施方案》，方案中提出加快推进“柔顺自适应人机交互等新技术在养老服务领域中的应用”。与人或周围物体接触，进行安全、柔顺的物理交互是现代机器人应具有的重要能力，也是机器人在各领域得以发挥作用的基础，相关文献围绕如何提高机器人的柔顺作业能力，从多种角度提出了诸多的思路和方法。这些方法总体来说可以分为两大类，分别为机械结构类方法和控制类方法。机械结构类方法是指在机器人本体设计中采用柔性元件或柔性结构，如串联弹性驱动器(series elastic actuator，SEA)，变刚度驱动器(variable stiffness actuator，VSA)、气动肌肉、磁驱驱动器等，用以缓冲外力的冲击，这种方式实现的是被动柔顺性。控制类方法通过各种控制方法，如阻抗/导纳控制(impedance/admittance control)，共享控制(shared control)，力位混合控制(hybrid force/position control)等。
本文主要对基于控制算法实现柔顺性的方法进行综述，基于机械结构的方法不在本文的调查范围内。并且，控制算法的范畴也不仅仅局限于机器人的运动控制回路，还包括在机器人上层运动规划回路和更上层的任务调度回路实现柔顺性的方法。
机器人柔顺行为实现方法
图5 双侧上肢外骨骼Harmony
柔性装配机器人在军工电子、航空航天、船舶兵器等复杂装备制造领域的应用非常广泛。现阶段装配机器人大多基于相机、激光跟踪仪等位置测量系统控制机器人运动，实现硬装配，而对装配力度的掌握十分欠缺。一些电连接器和电路模块的价格非常昂贵，如果在插拔过程中力度过大造成损坏，会造成不可估量的损失。机器人柔顺性能够在感知微小接触力的基础上补偿机器人装配过程中工件的位姿误差，满足复杂装备制造企业的柔性装配需求，提高生产良率。
本文提出以下几个机器人柔顺实现技术的发展趋势：
1) 智能化技术。机器人柔顺性大多来源于对人的行为的学习和模仿，然而即便是那些对于人来说很简单的技能，如插盲孔、削果皮等，都需要机器人经过多次的学习和试错才能获取。当前快速发展的人工智能技术能够赋予机器人强大的学习能力和模仿能力，让机器人只需观察一次演示过程或者独自试错有限次数，甚至只根据一段技能描述的语句，就能获取柔顺操作的技能特征，学习到人的操作技能[129]。
2) 安全性控制技术。虽然机器人柔顺控制能够在一定程度上增加人机交互的安全性，但是机器人和环境的碰撞、装配中的工件损伤等安全隐患仍是目前制约机器人走向实际应用的重要因素。研究实现高安全性操作的机器人柔顺控制技术，对机器人作业过程中面临的诸多不确定性扰动进行快速检测和补偿，防止机器人损坏工件和伤害人类，是实现机器人柔顺控制方法走向实际应用的重要方向。
3) 多机协同控制技术。多机器人系统具备典型的分布式特征，机器人之间相互通信，增加了运动的冗余度和灵活度，为机器人柔顺技术提供了更多的可选择方向，具有单机器人系统无法比拟的优势。当然，如何协同多台机器人安全、高效的工作是控制领域的研究难点，也是机器人柔顺性技术的重点应用方向之一。
4) 脑机接口技术。脑机接口技术[130]能够检测人类的大脑神经活动，然后利用模式识别和机器学习等技术推断人类的意图，并将其转变为机器人的运动控制策略。脑机接口技术能够超前感知人类的意图，在人类行动前就对人的动作做出预测，将脑机接口技术与机器人运动控制技术结合，能够让机器人预判人的动作，留有足够的时间做出合适的决策，增加运动的柔顺性。随着脑机接口系统在识别准确率和传输稳定性等方面的性能逐渐提升，能够检测的人类脑神经活动指令逐渐复杂化，脑机接口技术和机器人柔顺控制技术的组合将成为未来人机交互方向的研究热点。
5) 数字孪生技术。数字孪生系统通过在信息空间中构建物理实体的虚拟模型，利用历史数据和实时数据对模型状态的演变规律进行监控和预测，从而仿真出对象在真实物理世界内的行为。利用数字孪生技术在信息世界中构建人类和机器人的孪生对象，能够积累学习人机交互过程的技能和经验，从而协调人和机器人的运动和决策，有利于机器人在人机交互过程中做出柔顺响应。因此，数字孪生驱动的人机协作[131]是未来机器人柔顺实现技术的一大趋势。
3
总结与展望
本文依据调整运动策略的控制回路将机器人柔顺行为实现方法分为在运动控制回路的实现方法、在路径规划回路的实现方法和在任务调度回路的实现方法；然后将作者搜集到的机器人柔顺控制相关的文献按照上述分类方式进行了整理，分析了每种方法实现机器人柔顺性的机理和柔顺性的展现形式；最后，本文展示了机器人柔顺实现技术在人机协作、医疗康复、柔性装配、家庭服务等领域的典型应用，并结合新时代新技术的发展情况对机器人柔顺实现技术的未来趋势进行了展望，以期为机器人柔顺行为实现技术的研究挖掘出新的方向。
▼滑动查看更多
参考文献
[1] LOSEY D P, MCDONALD C G, BATTAGLIA E, et al. A review of intent detection, arbitration, and communication aspects of shared control for physical human-robot interaction[J/OL]. Applied Mechanics Reviews, 2018, 70(1)[2024-06-21]. https://www.researchgate.net/publication/322745295. DOI: 10.1115/1.4039145. |
[2] SELVAGGIO M, COGNETTI M, NIKOLAIDIS S, et al. Autonomy in physical human-robot interaction: A brief survey[J]. IEEE Robotics and Automation Letters, 2021, 6(4): 7989-7996. doi: 10.1109/LRA.2021.3100603 |
[3] HOGAN N. Impedance control: An approach to manipulation: Part Ⅰ-Theory[J]. Journal of Dynamic Systems, Measurement and Control, 1985, 107(1): 1-7. doi: 10.1115/1.3140702 |
[4] HOGAN N. Impedance control: An approach to manipulation: Part Ⅱ-Implementation[J]. Journal of Dynamic Systems, Measurement and Control. 1985, 107(1): 8-16. doi: 10.1115/1.3140713 |
[5] HOGAN N. Impedance control: An approach to manipulation: Part Ⅲ-Applications[J]. Journal of Dynamic Systems, Measurement and Control. 1985, 107(1): 17-24. doi: 10.1115/1.3140701 |
[6] FERRAGUTI F, SECCHI C, FANTUZZI C. A tank-based approach to impedance control with variable stiffness[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2013: 4948-4953. |
[7] RASHAD R, ENGELEN J B C, STRAMIGIOLI S. Energy tank-based wrench/impedance control of a fully-actuated hexarotor: A geometric port-hamiltonian approach[C]//International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2019: 6418-6424. |
[8] OTT C, MUKHERJEE R, NAKAMURA Y. A hybrid system framework for unified impedance and admittance control[J]. Journal of Intelligent & Robotic Systems, 2015, 78(3): 359-375. |
[9] KEEMINK A Q L, VAN DER KOOIJ H, STIENEN A H A. Admittance control for physical human-robot interaction[J]. The International Journal of Robotics Research, 2018, 37(11): 1421-1444. doi: 10.1177/0278364918768950 |
[10] KANG G, OH H S, SEO J K, et al. Variable admittance control of robot manipulators based on human intention[J]. IEEE/ASME Transactions on Mechatronics, 2019, 24(3): 1023-1032. doi: 10.1109/TMECH.2019.2910237 |
[11] 李枭. 基于七轴机器人iiwa的人机协作技术研究[J]. 电子技术, 2021, 50(3): 32-33. https://www.cnki.com.cn/Article/CJFDTOTAL-DZJS202103015.htm LI X. Study on human machine cooperation technology based on seven axis robot iiwa[J]. Electronic Technology, 2021, 50(3): 32-33. https://www.cnki.com.cn/Article/CJFDTOTAL-DZJS202103015.htm |
[12] LIPPIELLO V, SICILIANO B, VILLANI L. A position-based visual impedance control for robot manipulators[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2007: 2068-2073. |
[13] CACCAVALE F, CHIACCHIO P, MARINO A, et al. Six-dof impedance control of dual-arm cooperative manipulators[J]. IEEE/ASME Transactions on Mechatronics, 2008, 13(5): 576-586. doi: 10.1109/TMECH.2008.2002816 |
[14] EIBAND T, SAVERIANO M, LEE D. Learning haptic exploration schemes for adaptive task execution[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2019: 7048-7054. |
[15] LI Y, GE S S, YANG C, et al. Model-free impedance control for safe human-robot interaction[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2011: 6021-6026. |
[16] LI Y, SAM G S, YANG C. Learning impedance control for physical robot-environment interaction[J]. International Journal of Control, 2012, 85(2): 182-193. doi: 10.1080/00207179.2011.642309 |
[17] MAGRINI E, FLACCO F, DE LUCA A. Estimation of contact forces using a virtual force sensor[C]//IEEE International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 2014: 2126-2133. |
[18] MAGRINI E, FLACCO F, DE LUCA A. Control of generalized contact motion and force in physical human-robot interaction[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2015: 2298-2304. |
[19] SALDARRIAGA C, CHAKRABORTY N, KAO I. Joint space stiffness and damping for Cartesian and null space impedance control of redundant robotic manipulators[C]//Proceedings in Advanced Robotics. Piscataway, USA: IEEE, 2019: 410-426. |
[20] HUO J, RU H, YANG B, et al. Air-chamber-based soft six-axis force/torque sensor for human-robot interaction[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73(2024): 1-12. |
[21] WANG C, LIU C, SHANG F, et al. Tactile sensing technology in bionic skin: A review[J]. Biosensors and Bioelectronics, 2023, 220: 1-18. |
[22] PAN M, SU T, LIANG K, et al. Sensorless force estimation of teleoperation system based on multilayer depth extreme learning machine[J]. Applied Soft Computing, 2024, 157(111494): 1-11. |
[23] TIAN Y, ZHANG C, JIANG S, et al. Noncontact cable force estimation with unmanned aerial vehicle and computer vision[J]. Computer-Aided Civil and Infrastructure Engineering, 2021, 36(1): 73-88. doi: 10.1111/mice.12567 |
[24] ALBU-SCHAFFER A, HIRZINGER G. Cartesian impedance control techniques for torque controlled light-weight robots[C]//International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2002: 657-663. |
[25] SALISBURY J K. Active stiffness control of a manipulator in cartesian coordinates[C]//IEEE Conference on Decision and Control. Piscataway, USA: IEEE, 1980: 95-100. |
[26] CHEN S F, KAO I. Conservative congruence transformation for joint and Cartesian stiffness matrices of robotic hands and fingers[J]. The International Journal of Robotics Research, 2000, 19(9): 835-847. doi: 10.1177/02783640022067201 |
[27] SONG P, YU Y, ZHANG X. Impedance control of robots: An overview[C]//2nd International Conference on Cybernetics, Robotics and Control. Piscataway, USA: IEEE, 2017: 51-55. |
[28] CALANCA A, MURADORE R, FIORINI P. A review of algorithms for compliant control of stiff and fixed-compliance robots[J]. IEEE/ASME Transactions on Mechatronics, 2015, 21(2): 613-624. |
[29] SONG P, YU Y, ZHANG X. A tutorial survey and comparison of impedance control on robotic manipulation[J]. Robotica, 2019, 37(5): 801-836. doi: 10.1017/S0263574718001339 |
[30] BALATTI P, KANOULAS D, TSAGARAKIS N G, et al. Towards robot interaction autonomy: explore, identify, and interact[C]//International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2019: 9523-9529. |
[31] PARENT D, COLOMé A, TORRAS C. Variable impedance control in Cartesian latent space while avoiding obstacles in null space[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2020: 9888-9894. |
[32] LEE D, OTT C. Incremental kinesthetic teaching of motion primitives using the motion refinement tube[J]. Autonomous Robots, 2011, 31(2): 115-131. |
[33] BIAN F F, LI R F, LIANG P D. SVM based simultaneous hand movements classification using sEMG signals[C]//IEEE International Conference on Mechatronics and Automation. Piscataway, USA: IEEE, 2017: 427-432. |
[34] PETERNEL L, PETRIC T, OZTOP E, et al. Teaching robots to cooperate with humans in dynamic manipulation tasks based on multi-modal human-in-the-loop approach[J]. Autonomous Robots, 2014, 36(1): 123-136. |
[35] VOGEL J, CASTELLINI C, VAN DER SMAGT P. EMG-based teleoperation and manipulation with the DLR LWR-Ⅲ[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 2011: 672-678. |
[36] YANG C, ZENG C, FANG C, et al. A dmps-based framework for robot learning and generalization of humanlike variable impedance skills[J]. IEEE/ASME Transactions on Mechatronics, 2018, 23(3): 1193-1203. doi: 10.1109/TMECH.2018.2817589 |
[37] BIAN F F, REN D M, LI R F, et al. Improving stability in physical human-robot interaction by estimating human hand stiffness and a vibration index[J]. Industrial Robot: An International Journal, 2019, 46(4): 529-540. doi: 10.1108/IR-05-2018-0111 |
[38] BIAN F F, LI R F, REN D M. Variable admittance control improving stability in physical human-robot interaction[C]//IEEE International Conference on Information and Automation. Piscataway, USA: IEEE, 2018: 1485-1490. |
[39] TSUMUGIWA T, YOKOGAWA R, HARA K. Variable impedance control based on estimation of human arm stiffness for human-robot cooperative calligraphic task[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2002: 644-650. |
[40] WAKITA K, HUANG J, DI P, et al. Human-walking-intention-based motion control of an omnidirectional-type cane robot[J]. IEEE/ASME Transactions on Mechatronics, 2013, 18(1): 285-296. doi: 10.1109/TMECH.2011.2169980 |
[41] VAROL H A, SUP F, GOLDFARB M. Multiclass real-time intent recognition of a powered lower limb prosthesis[J]. IEEE Transactions on Biomedical Engineering, 2010, 57(3): 542-551. doi: 10.1109/TBME.2009.2034734 |
[42] PHILIPS J, MILLAN J D R, VANACKER G, et al. Adaptive shared control of a brain-actuated simulated wheelchair[C]//10th IEEE International Conference on Rehabilitation Robotics. Piscataway, USA: IEEE, 2007: 408-414. |
[43] CARLSON T, MILLAN J D R. Brain controlled wheelchairs: A robotic architecture[J]. IEEE Robotics and Automation Magazine, 2013, 20(1): 65-73. doi: 10.1109/MRA.2012.2229936 |
[44] REBSAMEN B, GUAN C, ZHANG H, et al. A brain controlled wheelchair to navigate in familiar environments[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2010, 18(6): 590-598. doi: 10.1109/TNSRE.2010.2049862 |
[45] AARNO D, EKVALL S, KRAGIC D. Adaptive virtual fixtures for machine-assisted teleoperation tasks[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2005: 1139-1144. |
[46] YU W, ALQASEMI R, DUBEY R, et al. Tele-manipulation assistance based on motion intention recognition[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2005: 1121-1126. |
[47] BIAN F F, REN D M, LI R F, et al. Dynamical system based variable admittance control for physical human-robot interaction[J]. Industrial Robot: An International Journal, 2020, 47(4): 623-635. doi: 10.1108/IR-12-2019-0258 |
[48] WOLBRECHT E T, CHAN V, REINKENSMEYER D J, et al. Optimizing compliant model based robotic assistance to promote neuro rehabilitation[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2008, 16(3): 286-297. doi: 10.1109/TNSRE.2008.918389 |
[49] RAUTER G, SIGRIST R, MARCHAL-CRESPO L, et al. Assistance or challenge? filling a gap in user-cooperative control[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 2011: 3068-3073. |
[50] PEHLIVAN A U, LOSEY D P, O'MALLEY M K. Minimal assist-as-needed controller for upper limb robotic rehabilitation[J]. IEEE Transactions on Robotics, 2016, 32(1): 113-124. doi: 10.1109/TRO.2015.2503726 |
[51] EMKEN J L, BOBROW J E, REINKENSMEYER D J. Robotic movement training as an optimization problem: Designing a controller that assists only as needed[C]//9th International Conference on Rehabilitation Robotics. Piscataway, USA: IEEE, 2005: 307-312. |
[52] EVRARD P, KHEDDAR A. Homotopy switching model for dyad haptic interaction in physical collaborative tasks[C]//Symposium on Eurohaptics Conference. Piscataway, USA: IEEE, 2009: 45-50. |
[53] MEDINA J R, LORENZ T, HIRCHE S. Synthesizing anticipatory haptic assistance considering human behavior uncertainty[J]. IEEE Transactions on Robotics, 2015, 31(1): 180-190. doi: 10.1109/TRO.2014.2387571 |
[54] LI Y, TEE K P, CHAN W L, et al. Continuous role adaptation for human-robot shared control[J]. IEEE Transactions on Robotics, 2015, 31(3): 672-681. http://www1.i2r.a-star.edu.sg/~kptee/TRO-role-adaptation.pdf |
[55] THOBBI A, GU Y, SHENG W. Using human motion estimation for human-robot cooperative manipulation[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 2011: 2873-2878. |
[56] DRAGAN A D, SRINIVASA S S. A policy blending formalism for shared control[J]. The International Journal of Robotics Research, 2013, 32(7): 790-805. |
[57] IJSPEERT A J, NAKANISHI J, HOFFMANN H, et al. Dynamical movement primitives: Learning attractor models for motor behaviors[J]. Neural Computation, 2013, 25(2): 328-373. http://users.wpi.edu/~zli11/teaching/rbe595_2017/Assignment/Assignment12.pdf |
[58] COLOME A, TORRAS C. Dimensionality reduction for dynamic movement primitives and application to bimanual manipulation of clothes[J]. IEEE Transactions on Robotics, 2018, 34(3): 602-615. |
[59] PASTOR P, HOFFMANN H, ASFOUR T, et al. Learning and generalization of motor skills by learning from demonstration[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2009: 763-768. |
[60] YANG C, ZENG C, FANG C, et al. A dmps-based framework for robot learning and generalization of humanlike variable impedance skills[J]. IEEE/ASME Transactions on Mechatronics, 2018, 23(3): 1193-1203. |
[61] KOC O, MAEDA G, NEUMANN G, et al. Optimizing robot striking movement primitives with Iterative Learning Control[C]//15th IEEE-RAS International Conference on Humanoid Robots. Piscataway, USA: IEEE, 2015: 80-87. |
[62] BIAN F F, REN D M, LI R F, et al. An extended DMP framework for robot learning and improving variable stiffness manipulation[J]. Assembly Automation, 2019, 40(1): 85-94. |
[63] MAEDA G J, NEUMANN G, EWERTON M, et al. Probabilistic movement primitives for coordination of multiple human-robot collaborative tasks[J]. Autonomous Robots, 2017, 41(3): 593-612. |
[64] GAMS A, NEMEC B, IJSPEERT A J, et al. Coupling movement primitives: Interaction with the environment and bimanual tasks[J]. IEEE Transactions on Robotics, 2014, 30(4): 816-830. |
[65] NEMEC B, LIKAR N, GAMS A, et al. Human robot cooperation with compliance adaptation along the motion trajectory[J]. Autonomous Robots, 2018, 42(5): 1023-1035. |
[66] KHANSARI-ZADEH S M, BILLARD A. Learning stable non-linear dynamical systems with Gaussian mixture models[J]. IEEE Transaction on Robotics, 2011, 27(5): 943-957. |
[67] KHANSARI-ZADEH S M, KHATIB O. Learning potential functions from human demonstrations with encapsulated dynamic and compliant behaviors[J]. Autonomous Robots, 2017, 41(1): 45-69. |
[68] KHANSARI-ZADEH S M, KLINGBEIL E, KHATIB O. Adaptive human-inspired compliant contact primitives to perform surface-surface contact under uncertainty[J]. International Journal of Robotics Research, 2016, 35(13): 1651-1675. |
[69] KRONANDER K, KHANSARI-ZADEH S M, BILLARD A. Incremental motion learning with locally modulated dynamical systems[J]. Robotics and Autonomous Systems, 2015, 70: 52-62. |
[70] KHANSARI-ZADEH, BILLARD A. A dynamical system approach to real-time obstacle avoidance[J]. Autonomous Robots, 2012, 32(4): 433-454. |
[71] KHORAMSHAHI M, LAURENS A, TRIQUET T, et al. From human physical interaction to online motion adaptation using parameterized dynamical systems[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 2018: 1361-1366. |
[72] KHORAMSHAHI M, BILLARD A. A dynamical system approach for detection and reaction to human guidance in physical human-robot interaction[J]. Autonomous Robots, 2020, 44(8): 1411-1429. |
[73] KHATIB O. Real-time obstacle avoidance for manipulators and mobile robots[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 1985: 500-505. |
[74] MONTIEL O, OROZCO ROSAS U, SEPúLVEDA R. Path planning for mobile robots using Bacterial Potential Field for avoiding static and dynamic obstacles[J]. Expert Systems with Applications, 2015, 42(12): 5177-5191. |
[75] TRIHARMINTO H H, WAHYUNGGORO O, ADJI T B, et al. An integrated artificial potential field path planning with kinematic control for non-holonomic mobile robot[J]. International Journal on Advanced Science, Engineering and Information Technology, 2016, 6(4): 410-418. |
[76] TRIHARMINTO H H, WAHYUNGGORO O, ADJI T B, et al. Local information using stereo camera in artificial potential field based path planning[J]. IAENG International Journal of Computer Science, 2017, 44(3): 316-326. |
[77] MONTIEL O, OROZCO-ROSAS U, SEPULVEDA R. Path planning for mobile robots using bacterial potential field for avoiding static and dynamic obstacles[J]. Expert Systems with Applications, 2015, 42(12): 5177-5191. |
[78] ISWANTO I, MA'ARIF A, WAHYUNGGORO O, et al. Artificial potential field algorithm implementation for quadrotor path planning[J]. International Journal of Advanced Computer Science and Applications, 2019, 10(8): 575-585. |
[79] YUN G, WEI Z, GONG F, et al. Dynamic path planning for underwater vehicles based on modified artificial potential field method[C]//4th International Conference on Digital Manufacturing and Automation. Piscataway, USA: IEEE, 2013: 518-521. |
[80] ZHONG Q, JIE Z, TONG C. Tracking for humanoid robot based on Kinect[C]//International Conference on Mechatronics and Control. Piscataway, USA: IEEE, 2014: 1191-1194. |
[81] IGARASHI H, KAKIKURA M. Path and posture planning for walking robots by artificial potential field method[C]//IEEE International Conference on Robotics & Automation. Piscataway, USA: IEEE, 2004: 2165-2170. |
[82] SANCHO-PRADEL D L, SAAJ C M. Assessment of artificial potential field methods for navigation of planetary rovers[C]//2009 European Control Conference. Piscataway, USA: IEEE, 2009: 3027-3032. |
[83] WANG W, ZHU M, WANG X, et al. An improved artificial potential field method of trajectory planning and obstacle avoidance for redundant manipulators[J]. International Journal of Advanced Robotic Systems, 2018, 15(5): 1-13. |
[84] DU G, LONG S, LI F, et al. Active collision avoidance for human-robot interaction with UKF, expert system, and artificial potential field method[J]. Frontiers in Robotics and AI, 2018, 5: 1-11. |
[85] BROZ F, NOURBAKHSH I, SIMMONS R. Designing POMDP models of socially situated tasks[C]//IEEE International Symposium on Robot and Human Interactive Communication. Piscataway, USA: IEEE, 2011: 39-46. |
[86] HOROWITZ M, BURDICK J. Interactive non-prehensile manipulation for grasping via POMDPs[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2013: 3257-3264. |
[87] HSIAO K, KAELBLING L P, LOZANO-PEREZ T. Grasping POMDPs[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2007: 4685-4692. |
[88] KOVAL M C, POLLARD N S, SRINIVASA S S. Pre-and-post contact policy decomposition for planar contact manipulation under uncertainty[J]. International Journal of Robotics Research, 2016, 35(1/2/3): 244-264. |
[89] MONSO P, ALENY'A G, TORRAS C. POMDP approach to robotized clothes separation[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 2012: 1324-1329. |
[90] GARG F, HSU D, LEE W S. Learning to grasp under uncertainty using POMDPs[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2019: 2751-2757. |
[91] LI J K, HSU D, LEE W S. Act to see and see to act: POMDP planning for objects search in clutter[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 2016: 5701-5707. |
[92] XIAO Y, KATT S, TEN PAS A, et al. Online planning for target object search in clutter under partial observability[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2019: 8241-8247. |
[93] PAJARINEN J, KYRKI V. Robotic manipulation in object composition space[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 2014: 1-6. |
[94] PAJARINEN J, KYRKI V. Robotic manipulation of multiple objects as a POMDP[J]. Artificial Intelligence, 2017, 247(2017): 213-228. |
[95] PAJARINEN J, LUNDELL J, KYRKI V. POMDP planning under object composition uncertainty: Application to robotic manipulation[J]. IEEE Transactions on Robotics, 2023, 39(1): 41-56. |
[96] BAJCSY A, LOSEY D P, O'MALLEY M K, et al. Learning robot objectives from physical human interaction[J]. Journal of Machine Learning Research, 2017: 217-226. |
[97] CALINON S, GUENTER F, BILLARD A. On learning, representing, and generalizing a task in a humanoid robot[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2007, 37(2): 286-298 |
[98] CALINON S, LI Z B, ALIZADEH T, et al. Statistical dynamical systems for skills acquisition in humanoids[C]//12th IEEE-RAS International Conference on Humanoid Robots. Piscataway, USA: IEEE, 2012: 323-329. |
[99] PISTILLO A, CALINON S, CALDWELL D G. Bilateral physical interaction with a robot manipulator through a weighted combination of flow fields[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 2011: 3047-3052. |
[100] BANDYOPADHYAY T, JIE C Z, HSU D, et al. Intention-aware pedestrian avoidance[C]//Experimental Robotics. Berlin, Germany: Springer, 2013: 963-977. |
[101] RAVICHANDAR H C, DANI A. Human intention inference and motion modeling using approximate EM with online learning[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA: IEEE, 2015: 1819-1824. |
[102] WANG W, LI R, CHEN Y, et al. Human intention prediction in human-robot collaborative tasks[C]//ACM/IEEE International Conference on Human-Robot Interaction. Piscataway, USA: IEEE, 2018: 279-280. |
[103] 丁其川, 熊安斌, 赵新刚, 等. 基于表面肌电的运动意图识别方法研究及应用综述[J]. 自动化学报, 2016, 42(1): 13-25. https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO201601002.htm DING Q C, XIONG A B, ZHAO X G, et al. A review on researches and applications of sEMG-based motion intent recognition methods[J]. Acta Automatica Sinica, 2016, 42(1): 13-25. https://www.cnki.com.cn/Article/CJFDTOTAL-MOTO201601002.htm |
[104] BUSSY A, GERGONDET P, KHEDDAR A, et al. Proactive behavior of a humanoid robot in a haptic transportation task with a human partner[C]//21st IEEE International Symposium on Robot and Human Interactive Communication. Piscataway, USA: IEEE, 2012: 962-967. |
[105] CALINON S, BRUNO D, CALDWELL D G. A task-parameterized probabilistic model with minimal intervention control[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2014: 3339-3344. |
[106] EWERTON M, NEUMANN G, LIOUTIKOV R, et al. Learning multiple collaborative tasks with a mixture of interaction primitives[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA: IEEE, 2015: 1535-1542. |
[107] LEE S H, SUH I H, CALINON S, et al. Autonomous framework for segmenting robot trajectories of manipulation task[J]. Autonomous Robots, 2015, 38(2): 107-141. |
[108] KHORAMSHAHI M, BILLARD A. A dynamical system approach to task-adaptation in physical human-robot interaction[J]. Autonomous Robots, 2019, 43: 927-946. |
[109] 李林峰, 解永春. 空间机器人操作: 一种多任务学习视角[J]. 中国空间科学技术, 2022, 42(3): 10-24. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGKJ202203002.htm LI L F, XIE Y C. Space robotic manipulation: A multi-task learning perspective[J]. Chinese Space Science and Technology, 2022, 42 (3): 10-24. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGKJ202203002.htm |
[110] ROSS S, GORDON G, BAGNELL D. A reduction of imitation learning and structured prediction to no-regret online learning[C]//14th International Conference on Artificial Intelligence and Statistics. New York, USA: PMLR, 2011: 627-635. |
[111] LASKEY M, LEE J, FOX R, et al. DART: Noise injection for robust imitation learning[C]//1st Conference on Robot Learning. New York, USA: PMLR, 2017: 143-156. |
[112] SCHMIDHUBER J. On learning to think: Algorithmic information theory for novel combinations of reinforcement learning controllers and recurrent neural world models[EB/OL]. (2015-11-30)[2024-03-22]. https://arxiv.org/abs/1511.09249. |
[113] ANGELOV D, HRISTOV Y, BURKE M, et al. Composing diverse policies for temporally extended tasks[J]. IEEE Robotics and Automation Letters, 2020, 5(2): 2658-2665. |
[114] NACHUM O, AHN M, PONTE H, et al. Multi-agent manipulation via locomotion using hierarchical sim2real[C]//3rd Conference on Robot Learning. New York, USA: PMLR, 2019: 110-121. |
[115] FINN C, ABBEEL P, LEVINE S. Model-agnostic meta-learning for fast adaptation of deep networks[C]//34th International Conference on Machine Learning. New York, USA: PMLR, 2017: 1126-1135. |
[116] YU T, QUILLEN D, HE Z, et al. Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning[C]//3rd Conference on Robot Learning. New York, USA: PMLR, 2019: 1094-1100. |
[117] SOROKIN A Y, BURTSEV M S. Continual and multitask reinforcement learning with shared episodic memory[EB/OL]. (2019-05-07)[2024-03-22]. https://arxiv.org/abs/1905.02662. |
[118] TRAORé R, CASELLES-DUPRé H, LESORT T, et al. Continual reinforcement learning deployed in real-life using policy distillation and Sim2Real transfer[EB/OL]. (2019-01-11)[2024-03-22]. https://arxiv.org/abs/1906.04452. |
[119] PORTELAS R, HOFMANN K, OUDEYER P Y. Trying AGAIN instead of trying longer: Prior learning for automatic curriculum learning[EB/OL]. (2020-04-07)[2021-07-15]. https://arxiv.org/abs/2004.03168. |
[120] GOPINATHAN S, ÖTTING S K, STEIL J J. A user study on personalized stiffness control and task specificity in physical human-robot interaction[J]. Frontiers in Robotics and AI, 2017, 4: 1-16. |
[121] RAESSA M, CHEN J, WAN W, et al. Human-in-the-loop robotic manipulation planning for collaborative assembly[J]. IEEE Transactions on Automation Science and Engineering, 2020, 17(4): 1800-1813. |
[122] SHAHBAZI M, ATASHZA S F, TAVAKOLI M, et al. Robotics-assisted mirror rehabilitation therapy: A therapist-in-the-loop assist-as-needed architecture[J]. IEEE-ASME Transactions on Mechatronics, 2016, 21(4): 1954-1965. |
[123] KIM B, DESHPANDE A D. An upper-body rehabilitation exoskeleton harmony with an anatomical shoulder mechanism[J]. International Journal of Robotics Research, 2017, 36(4): 414-435. |
[124] 卢浩, 王洪波, 冯永飞. 下肢康复机器人人机耦合动力学建模和主动柔顺控制[J]. 机械工程学报, 2022, 58(7): 32-43. https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB202207004.htm LU H, WANG H B, FENG Y F. Human-machine coupling dynamics modeling and active compliance control of lower limb rehabilitation robot[J]. Journal of Mechanical Engineering, 2022, 58(7): 32-43. https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB202207004.htm |
[125] 李康康, 胡锦洋, 邢普, 等. 面向柔顺装配装夹的机器人手腕变刚度机理研究[J]. 机械工程学报, 2022, 58(19): 77-85. https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB202219008.htm LI K K, HU J Y, XING P, et al. Research on variable-stiffness mechanisms of robot wrists for compliant assembling-clamping[J]. Journal of Mechanical Engineering, 2022, 58(19): 77-85. https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB202219008.htm |
[126] 陈书清, 李铁民. 基于自适应柔顺控制的航天器部件装配[J]. 清华大学学报(自然科学版), 2023, 63(11): 1808-1819. https://www.cnki.com.cn/Article/CJFDTOTAL-QHXB202311011.htm CHEN S Q, LI T M. Spacecraft component assembly based on adaptive compliance control[J]. Journal of Tsinghua University (Science and Technology), 2023, 63(11): 1808-1819. https://www.cnki.com.cn/Article/CJFDTOTAL-QHXB202311011.htm |
[127] SIAN N, SAKAGUCHI T, YOKOI K, et al. Operating humanoid robots in human environments[C]//Workshop: Manipulation for Human Environments. Cambridge, USA: RSS, 2006: 1-6. |
[128] PARK D, HOSHI Y, MAHAJAN H, et al. Active robot-assisted feeding with a general-purpose mobile manipulator: Design, evaluation, and lessons learned[J]. Robotics and Autonomous Systems, 2020, 124: 1-17. |
[129] 罗威, 李明富, 赵文权, 等. 基于力- 位图像学习的工业机器人柔顺装配方法研究[J]. 机械工程学报, 2022, 58(21): 69-77. https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB202221007.htm LUO W, LI M F, ZHAO W Q, et al. Research on flexible assembly method of industrial robot based on force-pose-image learning[J]. Journal of Mechanical Engineering, 2022, 58(21): 69-77. https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB202221007.htm |
[130] 许未晴, 陈磊, 隋秀峰等. 脑机接口——脑信息读取与脑活动调控技术[J]. 科学通报, 2023, 68(8): 927-943. https://www.cnki.com.cn/Article/CJFDTOTAL-KXTB202308008.htm XU W Q, CHEN L, SUI X F, et al. Brain-computer interface-Brain information reading and activity control[J]. Chinese Science Bulletin, 2023, 68(8): 927-943. https://www.cnki.com.cn/Article/CJFDTOTAL-KXTB202308008.htm |
[131] 杨赓, 周慧颖, 王柏村. 数字孪生驱动的智能人机协作: 理论、技术与应用[J]. 机械工程学报, 2022, 58(18): 279-291. https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB202218023.htm YANG G, ZHOU H Y, WANG B C. Digital twin-driven smart human-machine collaboration: Theory, enabling technologies and applications[J]. Journal of Mechanical Engineering, 2022, 58(18): 279-291. https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB202218023.htm |
END
