In human-robot collaborative assembly, the ability of robots to respond flexibly and accurately to human actions is critical to ensuring assembly quality. To address the challenges posed by non-standard actions and dynamic changes in assembly sequences, this paper proposes a collaborative method integrating unknown action recognition and operation sequence prediction. First, for untrained actions that may occur in actual assembly, an open-set recognition strategy based on a random forest classifier is designed, incorporating a posterior probability threshold to reject unknown actions. In a speed reducer assembly experiment, the method achieved recognition accuracy of 95% for known actions and 98.65% for unknown actions. Second, to cope with the diversity and real-time variation in assembly sequences, an improved hidden Markov model (HMM) combining incremental learning and a forgetting factor is developed, enabling rapid adaptation and efficient prediction of new assembly patterns. With a forgetting factor of 0.7, the prediction accuracy reached 97.22%. Experimental results demonstrate that the proposed method maintains high recognition and prediction performance under complex collaborative scenarios with action uncertainty and sequence variability. In conclusion, the method improves the safety and efficiency of collaboration and is highly generalizable to other dynamic and variable human-robot collaborative assembly tasks.
WUS S, FANGH N, WANGP, et al .A method for human-robot collaborative assembly action recognition based on skeleton data and transfer learning[J].Human Factors in Robots, Drones and Unmanned Systems, 2024:66-74.
[2]
NICORAM L, AMBROSETTIR, WIENSG J, et al. Human-robot collaboration in smart manufacturing:robot reactive behavior intelligence[J]. Journal of Manufacturing Science and Engineering, 2021, 143(3): 031009.
[3]
ZHANGX Y, TIANS B, LIANGX, et al .Early prediction of human intention for human-robot collaboration using transformer network[J].Journal of Computing and Information Science in Engineering, 2024, 24(5): 051003.
[4]
QUJ, LIY M, LIUC R, et al .Prediction of assembly intent for human-robot collaboration based on video analytics and hidden Markov model[J]. Computers, Materials & Continua, 2025, 84(2): 3787-3810.
[5]
HOFFMANG, BREAZEALC. Cost-based anticipatory action selection for human-robot fluency[J]. IEEE Transactions on Robotics, 2007, 23(5): 952-961.
[6]
VILLANIV, PINIF, LEALIF, et al. Survey on human-robot collaboration in industrial settings:safety, intuitive interfaces and applications[J].Mechatronics, 2018, 55: 248-266.
MAURTUAI, FERNANDEZI, KILDALJ, et al .Enhancing safe human-robot collaboration through natural multimodal communication[C]//2016 IEEE 21st International Conference on Emerging Technologies and Factory Automation (ETFA). September 6-9, 2016, Berlin, Germany. IEEE, 2016: 1-8.
MAY A, HUANGY T, ZHANGJ H, et al. K-means-CNN-based classification study of mixed alloy samples of complex grades[J].Spectroscopy and Spectral Analysis, 2025, 45(7): 1946-1952.(in Chinese)
[11]
吕丽丽.基于长短期记忆网络步行训练机器人柔顺化控制[D].沈阳:沈阳工业大学, 2021.
[12]
LÜ L L, Compliant control of walking rehabilitation training robot based on long short-term memory network [D]. Shenyang: Shenyang University of Technology, 2021. (in Chinese)
[13]
仝佳媛 .基于图神经网络的机器人抓取推理与决策研究[D]. 北京: 北京工业大学, 2022.
[14]
TONGJ Y .Study on robot grasping reasoning and decision based on graph neural network[D]. Beijing:Beijing University of Technology, 2022.(in Chinese)
[15]
KULIĆD N, TAKANOW, NAKAMURAY .Incremental learning, clustering and hierarchy formation of whole body motion patterns using adaptive hidden Markov chains[J]. The International Journal of Robotics Research, 2008, 27(7):761-784.
[16]
SCHEIRERW J, DE REZENDE ROCHAA, SAPKOTAA, et al .Toward open set recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(7):1757-1772.
[17]
LYUZ Y, GUTIERREZN B, BEKSIW J .MetaMax:improved open-set deep neural networks via weibull calibration[C]//2023 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW). January 3-7, 2023, Waikoloa, HI, USA.IEEE, 2023:439-443.
[18]
BENDALEA, BOULTT E .Towards open set deep networks[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). June 27-30, 2016, Las Vegas, NV, USA.IEEE, 2016:1563-1572.
[19]
GENGC X, HUANGS J, CHENS C .Recent advances in open set recognition:a survey[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(10):3614-3631.
[20]
BERTIS, ROSASCOA, COLLEDANCHISEM, et al .One-shot open-set skeleton-based action recognition[C]//2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids).November 28-30, 2022, Ginowan, Japan. IEEE, 2023:765-772.
[21]
AGANIAND, KÖHLERM, BAAKES, et al .How object information improves skeleton-based human action recognition in assembly tasks[EB/OL]. (2023-01-09)[2025-08-15].
[22]
FENGG C, DESAID, PASQUALIS, et al. Open set recognition for random forest[EB/OL]. (2024-08-01)[2025-08-15].
[23]
CORTESEA, SOLBIATIS, SCANDELLIA, et al. Open-set recognition of human activities from head-mounted inertial sensor[J]. Sensors, 2026, 26(3): 1079.
[24]
GEZ Y, DEMYANOVS, CHENZ T, et al .Generative OpenMax for multi-class open set classification[EB/OL].(2017-08-24)[2025-08-15].
[25]
KIMS, CHIH G, LIM H, et al. Higher-order relational reasoning for pedestrian trajectory prediction[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).June 16-22, 2024, Seattle, WA, USA. IEEE, 2024:15251-15260.
[26]
SALZMANNT, CHIANGH T L, RYLLM, et al. Robots that can see: Leveraging human pose for trajectory prediction[J]. IEEE Robotics and Automation Letters, 2023, 8(11): 7090-7097.
[27]
GUPTAA, JOHNSONJ, LIF F, et al. Social GAN:socially acceptable trajectories with generative adversarial networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.June 18-23, 2018, Salt Lake City, UT, USA.IEEE, 2018:2255-2264.
[28]
ABILKASSOVS, GENTNERM, SHINTEMIROVA, et al .Proactive robot task sequencing through real-time hand motion prediction in human-robot collaboration[J].Image and Vision Computing, 2025, 155:105443.
[29]
ZANCHETTINA M, CASALINOA, PIRODDIL, et al .Prediction of human activity patterns for human-robot collaborative assembly tasks[J].IEEE Transactions on Industrial Informatics, 2019, 15(7):3934-3942.
[30]
LIUH Y, WANGL H .Human motion prediction for human-robot collaboration[J].Journal of Manufacturing Systems, 2017, 44:287-294.
[31]
DELANGEM, ALJUNDIR, MASANAM, et al .A continual learning survey:Defying forgetting in classification tasks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021:1.
[32]
SCHÄLED, STOELENM F, KYRKJEBØE .Incremental learning of probabilistic movement primitives (ProMPs) for human-robot cooperation[EB/OL]. (2021-05-28)[2026-06-15].
[33]
SCHÄLED, STOELENM F, KYRKJEBØE. Continuous and incremental learning in physical human-robot cooperation using probabilistic movement primitives[C]//2022 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN). August 29-September 2,2022,Napoli,Italy. IEEE, 2022: 1216-1223.
[34]
PARISIG I, KEMKERR, PARTJ L, et al. Continual lifelong learning with neural networks:a review[J]. Neural Networks, 2019, 113:54-71.
[35]
SCHIEMERM, FANGL, DOBSONS, et al. Online continual learning for human activity recognition[J]. Pervasive and Mobile Computing, 2023, 93:101817.
基金资助
福建省科技重大专项专题项目(2024HZ026020)
Fujian Provincial Science and Technology Major Project(2024HZ026020)