At present, robots are widely used in the field of machinery manufacturing, which improves the production speed on the basis of ensuring the safety of workers. As a result, the traditional mode of enterprises based on manual operation has begun to be transformed into industrial robots as the main body. Construction machinery robots need to capture information about the surrounding environment in production operations. Traditional object recognition methods cannot adapt to complex working environments. Therefore, how to effectively identify target objects and successfully grasp objects has become a challenge for robots. In addition, the grasping detection(GD) method required by the robot to complete the task also relies on the known information of the target object and cannot effectively deal with the complex and changeable unknown environment. To this end, this paper designs a robot GD system based on deep learning, constructs a GD model and system framework through a convolutional neural network(CNN), and introduces a multi-target object grasping recognition algorithm to improve the grasping accuracy of the robot. The simulation experiment of the GD system proves that the accuracy rate of the system successfully grasping objects is over 95%.

Zabolotny Simons. Object Recognition and Grasping Detection Method of Construction Machinery Robot Relying on Deep Learning. Kinetic Mechanical Engineering (2021), Vol. 2, Issue 2: 9-17. https://doi.org/10.38007/KME.2021.020202.

[1] Ulrich M, Follmann P, Neudeck J H. A comparison of shape-based matching with deep-learning-based object detection. Tm - Technisches Messen, 2019, 86(11):685-698. https://doi.org/10.1515/teme-2019-0076

[2] Weber I, Bongartz J, Roscher R. Artificial and beneficial - Exploiting artificial images for aerial vehicle detection. ISPRS Journal of Photogrammetry and Remote Sensing, 2021, 175(8):158-170. https://doi.org/10.1016/j.isprsjprs.2021.02.015

[3] Hwang P J, Hsu C C, Wang W Y. Development of a Mimic Robot-Learning From Demonstration Incorporating Object Detection and Multiaction Recognition. IEEE Consumer Electronics Magazine, 2020, 9(3):79-87. https://doi.org/10.1109/MCE.2019.2956202

[4] Rouhafzay G, Cretu A M, Payeur P. Biologically Inspired Vision and Touch Sensing to Optimize 3D Object Representation and Recognition. IEEE Instrumentation and Measurement Magazine, 2021, 24(3):85-90. https://doi.org/10.1109/MIM.2021.9436099

[5] Tsuru M, Escande A, Tanguy A, et al. Online Object Searching by a Humanoid Robot in an Unknown Environment. IEEE Robotics and Automation Letters, 2021, PP(99):1-1.

[6] Rosenberger P, Cosgun A, Newbury R, et al. Object-Independent Human-to-Robot Handovers Using Real Time Robotic Vision. IEEE Robotics and Automation Letters, 2021, 6(1):17-23. https://doi.org/10.1109/LRA.2020.3026970

[7] Cortez W S, Oetomo D, Manzie C, et al. Technical Note for "Tactile-Based Blind Grasping: A Discrete-Time Object Manipulation Controller for Robotic Hands". IEEE Robotics and Automation Letters, 2020, PP(99):1-1.

[8] Puente P, Fischinger D, Bajones M, et al. Grasping objects from the floor in assistive robotics: real world implications and lessons learned. IEEE Access, 2019, 7(99):123725-123735. https://doi.org/10.1109/ACCESS.2019.2938366

[9] Bottarel F, Vezzani G, Pattacini U, et al. GRASPA 1.0: GRASPA is a Robot Arm graSping Performance BenchmArk. IEEE Robotics and Automation Letters, 2020, 5(2):836-843. https://doi.org/10.1109/LRA.2020.2965865

[10] Hasegawa S, Yamaguchi N, Okada K, et al. Online Acquisition of Close-Range Proximity Sensor Models for Precise Object Grasping and Verification. IEEE Robotics and Automation Letters, 2020, PP(99):1-1.

[11] Bunis H A, Rimon E D. Toward Grasping Against the Environment: Locking Polygonal Objects Against a Wall Using Two-Finger Robot Hands. IEEE Robotics and Automation Letters, 2019, 4(1):105-112. https://doi.org/10.1109/LRA.2018.2882865

[12] Ishak A J, Mahmood S N. Eye in hand robot arm based automated object grasping system. Periodicals of Engineering and Natural Sciences (PEN), 2019, 7(2):555-566. https://doi.org/10.21533/pen.v7i2.528

[13] Sarakon P, Kawano H, Shimonomura K, et al. Improvement of Shrinking CNN Architecture Using Weight Sharing and Knowledge Distillation for Tactile Object Recognition. ICIC Express Letters, 2021, 12(7):627-633.

[14] Takeuchi M, Kawakubo H, Saito K, et al. ASO Visual Abstract: Automated Surgical Phase Recognition for Robot-Assisted Minimally Invasive Esophagectomy Using Artificial Intelligence. Annals of Surgical Oncology, 2021, 29(11):6858-6859. https://doi.org/10.1245/s10434-022-12006-0

[15] Brosque C, Fischer M. safety qua1ity schedu1e and cost impacts of 10 construction robots. Construction Robotics, 2021, 6(2):163-186. https://doi.org/10.1007/s41693-022-00072-5

[16] Bobkov V A, Kudryashov A P, Inzartsev A V. Object Recognition and Coordinate Referencing of an Autonomous Underwater Vehicle to Objects via Video Stream. Programming and Computer Software, 2021, 48(5):301-311. https://doi.org/10.1134/S0361768822050024

[17] Ko J H. Robot Vision System based on 3D Depth map and Object Recognition. Journal of the Institute of Electronics and Information Engineers, 2020, 57(3):101-105. https://doi.org/10.5573/ieie.2020.57.3.101

[18] A Kovács, Erds F G, Tipary B. Planning and Optimization of Robotic Pick-And-Place Operations in Highly Constrained Industrial Environments. Assembly Automation, 2021, 41(5):626-639. https://doi.org/10.1108/AA-07-2020-0099

[19] Hanafusa M, Ishikawa J. Mechanical Impedance Control of Cooperative Robot during Object Manipulation Based on External Force Estimation Using Recurrent Neural Network. Unmanned Systems, 2020, 08(03):239-251. https://doi.org/10.1142/S230138502050017X