{"title":"机械艺术书写——在可塑材料表面绘制符号的再现","authors":"Xin He;Teresa Zielinska;Takafumi Matsumaru;Vibekananda Dutta","doi":"10.1109/JSEN.2025.3555571","DOIUrl":null,"url":null,"abstract":"Existing surface shaping methods focus on hard materials with stable physical properties. This means that the approaches developed are insufficient for shaping soft materials. The article describes a cheap method of reproducing plastic deformations using a robotic manipulator. The shape recording and reproduction system consists of two RGB-D cameras, two containers with kinetic sand, and a manipulator with 6 degrees of freedom (DOF). Volunteers create templates by drawing on the surface of kinetic sand with a wooden stylus or finger. Some pressure is exerted while writing. The resulting shapes recorded by the RGB-D camera have the form of ribbon ditches (grooves). The obtained point cloud is processed to create a sand deformation model. In the first stage, a dedicated local smoothing technique is used. Then, special algorithms are implemented to create a description of the main curvatures and key dimensions of recorded signs. A spline-based approach is used. The method allows for the representation of various shapes in a unified form. In the final stage, modulated sinusoidal functions define the robot’s trajectory. The effects of the robot’s operation are recorded to assess the reproduction quality. The point cloud structural similarity measure (Point SSIM) evaluates the results. Experimental research takes into account many different shapes. Copies of shapes created by humans and robots are compared with the originals. The outcomes show that the quality of reproduction achieved by humans and robots is comparable. The median-based curvature similarity measure obtained for the human was only 1.92% higher than the robot’s result, and the covariance-based geometric similarity measure was only 0.74% higher than the robot’s score. The system can be used to mass-produce souvenirs or special implants.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 10","pages":"18090-18105"},"PeriodicalIF":4.3000,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Robotic Artistic Writing—Reproduction of Signs Drawn on the Surface of Plastically Deformable Materials\",\"authors\":\"Xin He;Teresa Zielinska;Takafumi Matsumaru;Vibekananda Dutta\",\"doi\":\"10.1109/JSEN.2025.3555571\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Existing surface shaping methods focus on hard materials with stable physical properties. This means that the approaches developed are insufficient for shaping soft materials. The article describes a cheap method of reproducing plastic deformations using a robotic manipulator. The shape recording and reproduction system consists of two RGB-D cameras, two containers with kinetic sand, and a manipulator with 6 degrees of freedom (DOF). Volunteers create templates by drawing on the surface of kinetic sand with a wooden stylus or finger. Some pressure is exerted while writing. The resulting shapes recorded by the RGB-D camera have the form of ribbon ditches (grooves). The obtained point cloud is processed to create a sand deformation model. In the first stage, a dedicated local smoothing technique is used. Then, special algorithms are implemented to create a description of the main curvatures and key dimensions of recorded signs. A spline-based approach is used. The method allows for the representation of various shapes in a unified form. In the final stage, modulated sinusoidal functions define the robot’s trajectory. The effects of the robot’s operation are recorded to assess the reproduction quality. The point cloud structural similarity measure (Point SSIM) evaluates the results. Experimental research takes into account many different shapes. Copies of shapes created by humans and robots are compared with the originals. The outcomes show that the quality of reproduction achieved by humans and robots is comparable. The median-based curvature similarity measure obtained for the human was only 1.92% higher than the robot’s result, and the covariance-based geometric similarity measure was only 0.74% higher than the robot’s score. The system can be used to mass-produce souvenirs or special implants.\",\"PeriodicalId\":447,\"journal\":{\"name\":\"IEEE Sensors Journal\",\"volume\":\"25 10\",\"pages\":\"18090-18105\"},\"PeriodicalIF\":4.3000,\"publicationDate\":\"2025-04-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Sensors Journal\",\"FirstCategoryId\":\"103\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10948877/\",\"RegionNum\":2,\"RegionCategory\":\"综合性期刊\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Sensors Journal","FirstCategoryId":"103","ListUrlMain":"https://ieeexplore.ieee.org/document/10948877/","RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
Robotic Artistic Writing—Reproduction of Signs Drawn on the Surface of Plastically Deformable Materials
Existing surface shaping methods focus on hard materials with stable physical properties. This means that the approaches developed are insufficient for shaping soft materials. The article describes a cheap method of reproducing plastic deformations using a robotic manipulator. The shape recording and reproduction system consists of two RGB-D cameras, two containers with kinetic sand, and a manipulator with 6 degrees of freedom (DOF). Volunteers create templates by drawing on the surface of kinetic sand with a wooden stylus or finger. Some pressure is exerted while writing. The resulting shapes recorded by the RGB-D camera have the form of ribbon ditches (grooves). The obtained point cloud is processed to create a sand deformation model. In the first stage, a dedicated local smoothing technique is used. Then, special algorithms are implemented to create a description of the main curvatures and key dimensions of recorded signs. A spline-based approach is used. The method allows for the representation of various shapes in a unified form. In the final stage, modulated sinusoidal functions define the robot’s trajectory. The effects of the robot’s operation are recorded to assess the reproduction quality. The point cloud structural similarity measure (Point SSIM) evaluates the results. Experimental research takes into account many different shapes. Copies of shapes created by humans and robots are compared with the originals. The outcomes show that the quality of reproduction achieved by humans and robots is comparable. The median-based curvature similarity measure obtained for the human was only 1.92% higher than the robot’s result, and the covariance-based geometric similarity measure was only 0.74% higher than the robot’s score. The system can be used to mass-produce souvenirs or special implants.
期刊介绍:
The fields of interest of the IEEE Sensors Journal are the theory, design , fabrication, manufacturing and applications of devices for sensing and transducing physical, chemical and biological phenomena, with emphasis on the electronics and physics aspect of sensors and integrated sensors-actuators. IEEE Sensors Journal deals with the following:
-Sensor Phenomenology, Modelling, and Evaluation
-Sensor Materials, Processing, and Fabrication
-Chemical and Gas Sensors
-Microfluidics and Biosensors
-Optical Sensors
-Physical Sensors: Temperature, Mechanical, Magnetic, and others
-Acoustic and Ultrasonic Sensors
-Sensor Packaging
-Sensor Networks
-Sensor Applications
-Sensor Systems: Signals, Processing, and Interfaces
-Actuators and Sensor Power Systems
-Sensor Signal Processing for high precision and stability (amplification, filtering, linearization, modulation/demodulation) and under harsh conditions (EMC, radiation, humidity, temperature); energy consumption/harvesting
-Sensor Data Processing (soft computing with sensor data, e.g., pattern recognition, machine learning, evolutionary computation; sensor data fusion, processing of wave e.g., electromagnetic and acoustic; and non-wave, e.g., chemical, gravity, particle, thermal, radiative and non-radiative sensor data, detection, estimation and classification based on sensor data)
-Sensors in Industrial Practice