To improve the accuracy of deep neural networks in solving inverse kinematics for redundant robots and reduce the probability of self-collision solutions, a solution method was proposed based on the conditional normalizing flows model. An improved L-M algorithm was employed to perform secondary optimization on the initial solutions generated by the conditional normalizing flows model to enhance computational accuracy. Furthermore, by training a multi-layer perceptron with extracted self-collision prior knowledge, a self-collision solution detector was constructed to filter out self-collision solutions. The results demonstrate that the calculated positional and angular errors remain below 0.01 mm and 0.1° respectively, the self-collision rate is maintained under 0.1%, and the single computation time is consistently within 10 ms. This method enables efficient and stable solutions for inverse kinematics problems in redundant robots.
综上所述,针对冗余机器人控制问题,如何快速精确地计算其逆运动学解,减少对样本数量的依赖以满足不同应用场景的需求,同时兼顾解集的丰富性和可行性,是当前有待解决的问题。 针对以上挑战,本文在L-M(Levenberg-Marquardt)算法与条件可逆网络的基础上,提出一种基于条件标准化流模型的冗余机器人逆运动学求解方法(normalizing optimization with conditional flows for inverse kinematics,NOC-IK)。该方法旨在降低L-M算法对初始值的敏感性,并充分利用机器人冗余特性,结合条件标准化流模型快速生成多样化和高质量的冗余机器人逆运动学解。针对自碰撞解检测问题,采用多层感知机评估碰撞成本,剔除解集中可能存在的自碰撞解,以确保机器人的运动可靠性。
在训练过程中使用SoftFlow[17]进行训练策略优化,具体将输入变量 x 和条件变量 c 按下式进行Softflow噪声处理:
其中,C为潜在噪声缩放因子,该参数值决定了从潜在分布中抽取的噪声幅度和范围, I 为单位阵, v 为从潜在分布中抽样并乘以噪声缩放尺度C的噪声。将缩放因子C添加到条件变量 c 后,得到更新后的条件变量[ cC],在后续推理过程中可将C置为0以消除引入噪声的影响。综合缩放函数与缩放因子C,可构造如下的对数似然损失函数:
为了确保实验结论的客观性,本节分别采用7自由度Panda、Kuka-Iiwa7和8自由度Fetch三种型号的冗余机器人对本文方法进行模拟仿真测试和性能评估。需要说明的是,本文方法对7自由度及以上具有机械臂结构的冗余机器人均是适用的。用于机器人建模的URDF文件是由机器人厂家官方提供的,该文件用于描述机器人的几何结构和动力学特性。利用Python中的机器人库(ROS)加载URDF文件,并模拟实际求解过程以评估算法的精度和速度。如表1所示,按照最大均值差异(maximum mean discrepancy, MMD)得分,选择最接近0的生成质量最好的模型进行初始解的生成。
QunwenOU, YUNChao, YANGXuebing, et al. Algorithm Based on Neural Network for Inverse Kinematics of Redundant Manipulator[J] Journal of Mechanical & Electrical Engineering, 2016,33 (6): 663-667.
LIJin, LIUXuan, ZHANGJianhua, et al. Research on Indirect Solution of Inverse Kinematics Based on RBF Neural Network[J]. Machine Tool & Hydraulics, 2019,47(23):32-37.
LIUShiping, CAOJunfeng, SUNTao, et al. Inverse Kinematics Analysis of Redundant Manipulators Based on BP Neural Network[J]. China Mechanical Engineering,2019,30(24):2974-2977.
LIUShiping, XIAWenjie, CHENMeng, et al. Inverse Kinematics Solution of Redundant Manipulator Based on Convolution Neural Networks[J]. Manned Spaceflight,2022,28(1):10-15.
SHIJianping. Inverse Kinematics Solution of Redundant Manipulator Based on Particle Swarm Optimization Algorithm[J]. Journal of Guiyang University(Natural Sciences),2020,15(3):48-52.
[11]
ARDIZZONEL, KRUSEJ, WIRKERTS, et al. Analyzing Inverse Problems with Invertible Neural Networks[C]∥International Conference on Learning Representations (ICLR).New Orleans, 2019:1808.04730.
[12]
GARGS, DUDEJAS, RASTOGIV. Inverse Kinematics of Tendon Driven Continuum Robots Using Invertible Neural Network[C]∥2022 2nd International Conference on Computers and Automation (CompAuto). Paris, 2022: 82-86.
[13]
AMESB, MORGANJ, KONIDARISG. IKFLOW: Generating Diverse Inverse Kinematics Solutions[J]. IEEE Robotics and Automation Letters, 2022, 7(3): 7177-7184.
[14]
PAPAMAKARIOSG, NALISNICKE, JIMENEZ REZENDED, et al. Normalizing Flows for Probabilistic Modeling and Inference[J]. Journal of Machine Learning Research,2019, 57(22):64.
[15]
KINGMA D P, DHARIWAL P. GLOW: Generative Flow with Invertible 1×1 Convolutions[C]∥The 32nd International Conference on Neural Information Processing Systems (NIPS'18). Red Hook, 2018: 10236-10245.
[16]
BEESONP, AMESB. TRAC-IK: an Open-source Library for Improved Solving of Generic Inverse Kinematics[C]∥2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids). Seoul, 2015: 928-935.
[17]
HABEKOSTJ G, STRAHLE, ALLGEUERP, et al. CycleIK: Neuro-inspired Inverse Kinematics[C]∥ International Conference on Artificial Neural Networks. Heraklion, 2023: 457-470.
[18]
ZHUJ Y, PARKT, ISOLAP, et al. Unpaired Image-to-image Translation Using Cycle-consistent Adversarial Networks [C] ∥Proceedings of the IEEE International Conference on Computer Vision. Venice, 2017: 2223-2232.
[19]
KERZELM, ALLGEUERP, STRAHLE, et al. Nicol: a Neuro-inspired Collaborative Semi-humanoid Robot that Bridges Social Interaction and Reliable Manipulation[J].IEEE Access,2023, 11: 123531-123542.
[20]
DEMBY’SJ, GAOY, DESOUZAG N. A Study on Solving the Inverse Kinematics of Serial Robots Using Artificial Neural Network and Fuzzy Neural Network[C]∥2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).New Orleans, 2019: 1-6.
[21]
GILBERTE G, FOOC P. Computing the Distance between General Convex Objects in Three-dimensional Space[J]. IEEE Transactions on Robotics and Automation, 1990, 6(1): 53-61.
[22]
SAFEEAM, NETOP, BEAREER. Efficient Calculation of Minimum Distance Between Capsules and Its Use in Robotics[J]. IEEE Access, 2018, 7: 5368-5373.
[23]
NVIDIAGPU Technology Conference GTC). Warp: a High-performance Python Framework for GPU Simulation and Graphics[EB/OL].(2022-03-31)[2025-01-03].
[24]
KIMH, LEEH, KANGW H, et al. Softflow: Probabilistic Framework for Normalizing Flow on Manifolds[J]. Neural Information Processing Systems, 2020, 33: 16388-16397.
[25]
PADMANABHAG A, ZABARASN. Solving Inverse Problems Using Conditional Invertible Neural Networks[J]. Journal of Computational Physics, 2021, 433: 110194.
LIJia, QIUWei, ZOUShaofen. Research on Magnetic Target Localization Based on Improved LM-GN Algorithm[J]. Digital Ocean & Underwater Warfare, 2023,6(5):552-561.
LIGuoming, SUMengyao, ZHUDaixian. An Improved LM Algorithm in Bundle Adjustment[J]. Journal of Xi'an University of Science and Technology, 2022,42(1): 152-159.
[30]
RAKITAD, MUTLUB, GLEICHERM. RelaxedIK: Real-time Synthesis of Accurate and Feasible Robot Arm Motion[C]∥Robotics: Science and Systems (RSS 2018.Pittsburgh, 2018:46968269.