In current small batch and customized production mode, the products change rapidly and the personal
demand increases sharply. Human-robot cooperation combining the advantages of human and robot is an effective
way to solve the complex assembly. However, the poor reusability of historical assembly knowledge reduces the
adaptability of assembly system to different tasks. For cross-domain strategy transfer, we propose a human-robot
cooperative assembly (HRCA) framework which consists of three main modules: expression of HRCA strategy,
transferring of HRCA strategy, and adaptive planning of motion path. Based on the analysis of subject capability
and component properties, the HRCA strategy suitable for specific tasks is designed. Then the reinforcement
learning is established to optimize the parameters of target encoder for feature extraction. After classification and
segmentation, the actor-critic model is built to realize the adaptive path planning with progressive neural network.
Finally, the proposed framework is verified to adapt to the multi-variety environment, for example, power lithium
batteries.
LÜ Qibing (吕其兵), LIU Tianyuan (刘天元), ZHANG Rong (张荣), JIANG Yanan (江亚南), XIAO Lei (肖雷), BAO Jingsong∗ (鲍劲松)
. Generation Approach of Human-Robot Cooperative Assembly Strategy Based on Transfer Learning[J]. Journal of Shanghai Jiaotong University(Science), 2022
, 27(5)
: 602
-613
.
DOI: 10.1007/s12204-022-2493-7
[1] LIU Z H, WANG X R, CAI Y J, et al. Dynamic risk assessment and active response strategy for industrial human-robot collaboration [J]. Computers & Industrial Engineering, 2020, 141: 106302.
[2] HUANG J, PHAM D T, LI R Y, et al. An experimental human-robot collaborative disassembly cell [J]. Computers & Industrial Engineering, 2021, 155: 107189.
[3] RENU R S, MOCKO G. Computing similarity of textbased assembly processes for knowledge retrieval and reuse [J]. Journal of Manufacturing Systems, 2016, 39: 101-110.
[4] DARVISH K, WANDERLINGH F, BRUNO B, et al. Flexible human-robot cooperation models for assisted shop-floor tasks [J]. Mechatronics, 2018, 51: 97-114.
[5] ABUDUWEILI A, LI S Y, LIU C L. Adaptable human intention and trajectory prediction for human-robot collaboration [DB/OL]. (2019-09-11). https://arxiv.org/abs/1909.05089.
[6] CHENG Y J, SUN L T, LIU C L, et al. Towards better human robot collaboration with robust plan recognition and trajectory prediction [DB/OL].(2020-02-17). https://arxiv.org/abs/1903.02199.
[7] LIU H Y, WANG L H. Collision-free human-robot collaboration based on context awareness [J]. Robotics and Computer-Integrated Manufacturing, 2021, 67: 101997.
[8] AMORIM A, GUIMARES D, MENDONA T, et al. Robust human position estimation in cooperative robotic cells [J]. Robotics and Computer-Integrated Manufacturing, 2021, 67: 102035.
[9] MAKRIS S, KARAGIANNIS P, KOUKAS S, et al. Augmented reality system for operator support in human-robot collaborative assembly [J]. CIRP Annals, 2016, 65(1): 61-64.
[10] RAATZ A, BLANKEMEYER S, RECKER T, et al. Task scheduling method for HRC workplaces based on capabilities and execution time assumptions for robots [J]. CIRP Annals, 2020, 69(1): 13-16.
[11] LIU H Y, WANG L H. Human motion prediction for human-robot collaboration [J]. Journal of Manufacturing Systems, 2017, 44: 287-294.
[12] BERG J, RECKORDT T, RICHTER C, et al. Action recognition in assembly for human-robot-cooperation using hidden Markov models [J]. Procedia CIRP, 2018, 76: 205-210.
[13] LI Z, JIN X L, JIA H Y, et al. The knowledge representation and reuse in product design [J]. Journal of Shanghai Jiao Tong University, 2006, 40(7): 1183- 1186 (in Chinese).
[14] HE L L, GUO W, JIANG P Y. A decision-making model for knowledge collaboration and reuse through scientific workflow [J]. Advanced Engineering Informatics, 2021, 49: 101345.
[15] ARANA-AREXOLALEIBA N, URRESTILLAANGUIOZAR N, CHRYSOSTOMOU D, et al. Transferring human manipulation knowledge to industrial robots using reinforcement learning [J]. Procedia Manufacturing, 2019, 38: 1508-1515.
[16] RAZIEI Z, MOGHADDAM M. Adaptable automation with modular deep reinforcement learning and policy transfer [J]. Engineering Applications of Artificial Intelligence, 2021, 103: 104296.
[17] RODR′IGUEZ I, NOTTENSTEINER K, LEIDNER D, et al. Pattern recognition for knowledge transfer in robotic assembly sequence planning [J]. IEEE Robotics and Automation Letters, 2020, 5(2): 3666-3673.
[18] GUO M H, CAI J X, LIU Z N, et al. PCT: Point cloud transformer [J]. Computational Visual Media, 2021, 7(2): 187-199.
