To address collision risks between autonomous guided vehicles and pedestrians in workshop environments, this study proposes a trajectory prediction-based collision warning method for unmanned forklifts and pedestrians. A pedestrian trajectory prediction model based on an autoencoder is first designed to enable end-to-end trajectory prediction using factory surveillance data. The three-dimensional human-machine distance is then computed based on monocular camera distance recovery principles. A fuzzy logic-based collision risk grading and warning model is developed to quantify potential collision risks into actionable warning levels for real-time safety interventions. Experimental results demonstrate that the proposed method effectively detects and predicts pedestrian movements in dynamic workshop environments with high confidence and low latency, reducing potential collision risks and improving workplace safety.
YunLHuLHaimaY, et al. Fusion of target detection and DWA algorithm for AGV path. Electron Sci Technol2024; 37(07): 33–42.
2.
ChenbeisiZZhiqiuH.A review of the development of automated guided vehicles (AGV). China Manuf Inform Tech2010; 39(01): 53–59.
3.
PaneruSJeelaniI.Computer vision applications in construction: current state, opportunities & challenges. Autom Constr2021; 132: 103940.
4.
TeizerJAllreadBSFullertonCE, et al. Autonomous pro-active real-time construction worker and equipment operator proximity safety alert system. Autom Constr2010; 19(5): 630–640.
5.
ChenHLuoXZhengZ, et al. A proactive workers’ safety risk evaluation framework based on position and posture data fusion. Autom Constr2019; 98: 275–288.
6.
ChaeSYoshidaT.Application of RFID technology to prevention of collision accident with heavy equipment. Autom Constr2010; 19(3): 368–374.
7.
Wei-LiFLie-YunD.Research on intelligent identification and correction of workers’ unsafe behaviours. Journal of Huazhong2022; 50: 5.
8.
ZhangMCaoTZhaoX.Applying sensor-based technology to improve construction safety management. Sensors2017; 17: 1841.
9.
HouXLiCFangQ.Computer vision-based safety risk computing and visualization on construction sites. Autom Constr2023; 156: 105129.
10.
KimDLiuMLeeS, et al. Remote proximity monitoring between mobile construction resources using camera-mounted UAVs. Autom Constr2019; 99: 168–182.
11.
LiZYuBWangY, et al. A novel collision warning system based on the visual road environment schema: an examination from vehicle and driver characteristics. Accid Anal Prev2023; 190: 107154.
12.
TangLWenMShanZ, et al. Digital twin-enabled efficient federated learning for collision warning in intelligent driving. IEEE Trans Intell Transp Syst2023; 25(3): 2573–2585.
13.
DingYLuoX.Monocular 2D camera-based proximity monitoring for human-machine collision warning on construction sites. arXiv preprint arXiv:2305.17931, 2023.https://arxiv.org/abs/2305.17931
14.
ZhangYWangXZhuoK, et al. Research on pedestrian vehicle collision warning based on path prediction. In: 20237th international conference on transportation information and safety (ICTIS), Xi'an, China, 2023, pp. 1267–1272. IEEE.
15.
KumarNLeeSC.Human-machine interface in smart factory: a systematic literature review. Technol Forecast Soc Change2022; 174: 121284.
16.
LombardiIMonacoMGLCapeceS.European data and framework analysis of human-machine interaction in manufacturing 4.0: an update. Chem Eng Trans2024; 111: 199–204.
17.
BarattaACiminoALongoF, et al. Digital twin for human-robot collaboration enhancement in manufacturing systems: literature review and direction for future developments. Comput Ind Eng2024; 187: 109764.
18.
WojkeNBewleyAPaulusD. Simple online and realtime tracking with a deep association metric. In: 2017 IEEE international conference on image processing (ICIP), Beijing, China, 2017, pp. 3645–3649. IEEE.
19.
MangalamKAnYGiraseH, et al. From goals, waypoints & paths to long term human trajectory forecasting. In: Proceedings of the IEEE/CVF international conference on computer vision, Montreal, QC, Canada, 2021: 15233–15242. IEEE.
20.
ChenJKaoSHeH, et al. Run, don't walk: chasing higher FLOPS for faster neural networks. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Vancouver, BC, Canada, 2023, pp. 12021–12031.
21.
LiuRLehmanJMolinoP, et al. An intriguing failing of convolutional neural networks and the coordconv solution. Adv Neural Inf Process Syst2018; 31: 9628–9639.
22.
LiuRLehmanJMolinoP, et al. An intriguing failing of convolutional neural networks and the coordconv solution. Adv Neural Inf Process Syst2018; 31.
23.
BewleyAGeZOttL, et al. Simple online and realtime tracking. In: 2016 IEEE international conference on image processing (ICIP), Phoenix, AZ, USA, 2016, pp. 3464–3468. IEEE.
PellegriniSEssAVan GoolL. Improving data association by joint modeling of pedestrian trajectories and groupings. In: 2010 Proceedings of the 11th European conference on computer vision, part I, Heraklion, Crete, Greece, September 5-11, 2010, Springer Berlin Heidelberg, 2010: 452–465.
26.
Leal-TaixéLFenziMKuznetsovaA, et al. Learning an image-based motion context for multiple people tracking. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Columbus, OH, USA, 2014, pp. 3542–3549.
27.
AlahiAGoelKRamanathanV, et al. Social LSTM: human trajectory prediction in crowded spaces. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA, 2016, pp. 961–971.
28.
GuptaAJohnsonJFei-FeiL, et al. Social GAN: socially acceptable trajectories with generative adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Salt Lake City, UT, USA, 2018, pp. 2255–2264.
MohamedAQianKElhoseinyM, et al. Social-STGCNN: a social spatio-temporal graph convolutional neural network for human trajectory prediction. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, Seattle, WA, USA, 2020, pp. 14424–14432.
31.
YuanYWengXOuY, et al. Agentformer: agent-aware transformers for socio-temporal multi-agent forecasting. In: Proceedings of the IEEE/CVF international conference on computer vision, Montreal, QC, Canada, 2021, pp. 9813–9823.
