Advanced Applications of Industrial Robotics: New Trends and Possibilities

In the paper

“Achieved 49.1% mean average precision, processing images in real-time at 35.3 FPS on one single Nvidia GTX1080 GPU.”

What the sources say

• ?Not checked — no full text of the sourcecites [40] Yu, 2020, A novel detection fusion network for solid waste sorting, Int. J. Adv. Robot. Syst. source
• Disputed

  The running-time results (C. Industrial Object Recognition, p. 6) report 2–3 Hz on an NVIDIA TITAN X GPU, or up to 5 Hz with a lighter network and point-cloud down-sampling—not 35.3 FPS on a GTX1080. Table IV (p. 7) reports 80.85% instance-wise and 75.52% pixel-wise average precision, rather than the claimed 49.1% mean average precision. (LLM, conf=0.88)

  Checked by a reasoning model — may be wrong.

  cites [55] Sun, 2019, A novel weakly-supervised approach for RGB-D-based nuclear waste object detection, IEEE Sens. J. sourceExperimental — accuracy not yet measured

In the paper

“Analysing questionnaires completed by 79 hotel managers, it was concluded that robots have an advantage over human employees due to better data processing capabilities, work speed, protection of personal data, and fewer mistakes.”

What the sources say

• Supported

  The Methodology (Questionnaire) reports a final sample of 79 hotel managers. The Findings (General perceptions of managers towards service robots) state that managers perceived robots as having advantages over human employees in data processing, speed of work, protection of personal data, and making fewer mistakes. These are reported perceptions, not independently measured performance differences. (LLM, conf=0.94)

  cites [8] Ivanov, 2020, Hotel managers’ perceptions towards the use of robots: A mixed-methods approach, Inf. Technol. Tour. source

In the paper

“The main disadvantages of robots were listed as: lack of capability to provide personalised service; inability to handle complaints; lack of friendliness and politeness; inability to implement a special request that goes beyond their programming; and the lack of understanding of emotions.”

What the sources say

• Supported

  The Findings section (‘General perceptions of managers towards service robots’) lists managers’ concerns about personalised service, complaint handling, friendliness and politeness. It explicitly identifies inability to fulfil special requests beyond programming and lack of understanding of guests’ emotions as the biggest disadvantages. No page number is provided in our copy. (LLM, conf=0.93)

  cites [8] Ivanov, 2020, Hotel managers’ perceptions towards the use of robots: A mixed-methods approach, Inf. Technol. Tour. source

In the paper

“The authors proposed a set of performance metrics and compared four robotic systems for bin picking, and took first place in the Amazon Robotics Challenge 2017.”

What the sources say

• Partly supported

  The Introduction and Conclusions say the paper proposes performance metrics and compares four systems from the 2017 Amazon Robotics Challenge. Section 5.2 identifies MIT-Princeton as the winning team, but the paper does not describe a single proposed system that took first place; it proposes metrics for analyzing the systems. (LLM, conf=0.88)

  cites [36] Fujita, 2020, What are the important technologies for bin picking? Technology analysis of robots in competitions based on a set of performance metrics, Adv. Robot. sourceExperimental — accuracy not yet measured

In the paper

“In the proposed system, colour and height sorting efficiency is around 99%.”

What the sources say

• Supported

  The Abstract states that the proposed computer-vision sorter detects and sorts objects by colour and height at the same time. It also reports colour-and-height sorting efficiency of around 99%. (LLM, conf=0.95)

  cites [38] Shaikat, 2020, Computer Vision Based Industrial Robotic Arm for Sorting Objects by Color and Height, J. Eng. Adv. source
• Partly supported

  The Results and Discussion section says the robotic system sorts objects by colour and geometry, while Camera Calibration says it measures height to calculate dimensions—not that it sorts by height. The Conclusion reports 100% sorting accuracy, rather than around 99% efficiency. (LLM, conf=0.88)

  cites [53] Fadhil, 2020, Computer Vision-Based System for Classification and Sorting Color Objects, IOP Conf. Ser. Mater. Sci. Eng. sourceExperimental — accuracy not yet measured
• Partly supported

  The Introduction describes a camera-based sorter that checks granule colour, and the Conclusions report 99.81% purity in the accepted material. But that figure is purity, not colour-and-height sorting efficiency; the paper does not report height sorting, and its nine-class classification accuracy was 90.52%. (LLM, conf=0.88)

  cites [54] Peršak, T., Viltužnik, B., Hernavs, J., and Klancnik, S. (2020). Vision-Based Sorting Systems for Transparent Plastic Granulate. Appl. Sci., 10. sourceExperimental — accuracy not yet measured

In the paper

“The analysis shows that AR is mainly used to control and program robotic arms, visualise general tasks or robot information, and visualise the industrial robot workspace.”

What the sources say

• Supported

  The paper’s discussion of its review findings (section labelled 735) identifies these three uses: controlling or programming robotic arms, displaying task or robot information, and visualising the robot workspace. It qualifies the distribution: workspace visualisation accounts for only 15% of the collected works. (LLM, conf=0.93)

  cites [21] Manuri, 2020, A systematic review of Augmented Reality interfaces for collaborative industrial robots, Comput. Ind. Eng. source

In the paper

“During the experiments, the dVRL control policy was effectively learned, and it was found that it could be transferred to a realrobot-with minimal efforts.”

What the sources say

• Supported

  The Discussion and Conclusion states that dVRL control policies were effectively learned and transferred effectively to a real robot with minimal effort. The Experiments section also says the learned policies were transferred to the dVRK for evaluation. (LLM, conf=0.95)

  cites [63] Richter, F., Orosco, R.K., and Yip, M.C. (2019). Open-Sourced Reinforcement Learning Environments for Surgical Robotics. arXiv. source

In the paper

“Results of the analysis indicate that AR systems are faster than traditional approaches; users have greater appreciation for AR systems in terms of likeability and usability; and AR seems to reduce physical workload, whereas the impact on mental workload depends on the interaction interface [16].”

What the sources say

• Supported

  The review’s summary of AR strengths (around line 840) states all four points: faster task completion than traditional approaches, greater user appreciation for likeability and usability, reduced physical workload, and mental workload that depends on the interaction interface. The discussion around line 820 adds that mental workload may increase when AR is paired with speech interfaces. (LLM, conf=0.95)

  cites [21] Manuri, 2020, A systematic review of Augmented Reality interfaces for collaborative industrial robots, Comput. Ind. Eng. source
• ?Could not verify

  The Results and Discussions section evaluates machine-learning classifiers for induction-motor fault and cyberattack detection, not augmented-reality systems. Searches for AR speed, likeability, usability, and physical or mental workload found no passage addressing the cited claim. (LLM, conf=0.76)

  cites [16] Tran, 2021, Experimental Setup for Online Fault Diagnosis of Induction Machines via Promising IoT and Machine Learning: Towards Industry 4.0 Empowerment, IEEE Access sourceExperimental — accuracy not yet measured

In the paper

“Contrary to typical industrial robots, next-generation robotics uses artificial intelligence (AI) to collaboratively perform tasks and is suitable for uncontrolled/unpredictable environments [15].”

What the sources say

• Partly supported

  The Introduction and §2 describe a new generation of robots that work closely with humans and adapt their behaviour when a person enters their workspace. Section 2 also calls artificial intelligence a main element of the Industry 4.0 paradigm. The paper does not say that AI is what enables the collaboration, or establish that these robots are suitable for uncontrolled or unpredictable environments. (LLM, conf=0.86)

  cites [15] Galin, 2019, Automation and robotics in the context of Industry 4.0: The shift to collaborative robots, IOP Conf. Ser. Mater. Sci. Eng. sourceExperimental — accuracy not yet measured

In the paper

“The main issues are a lack of high-quality medical and surgical data, a lack of reliable metrics that adequately reflect learning characteristics, and a lack of a structured approach to the effective transfer of surgical skills for automated execution [64].”

What the sources say

• Supported

  The Conclusion (p. 12) lists high-quality data, skill-analysis metrics, and a pipeline for autonomous surgical action among the challenges for machine learning in surgical robotics. The High-quality Medical/Surgical Data section (p. 10), Learning and Defining Skill Analysis Metric section (p. 11), and pipeline discussion (p. 11) elaborate on each of the three issues in the claim. (LLM, conf=0.92)

  cites [64] Kassahun, 2016, Surgical robotics beyond enhanced dexterity instrumentation: A survey of machine learning techniques and their role in intelligent and autonomous surgical actions, Int. J. Comput. Assist. Radiol. Surg. source

In the paper

“In the area of path planning and optimisation, experiments have been conducted for automatic object and 3D position detection [82] quasi-static path optimisation [83], image analysis [84], path smoothing [85], BIM [86], and accurate self-localisation in harsh industrial environments [80,81].”

What the sources say

• Supported

  The Abstract describes a robotic pick-and-place system that uses a 3D camera to recognize objects, calculate their positions, and generate a path to grasp them. Citation [82] is attached to automatic object and 3D position detection; the other listed topics have separate citations and are not attributed to this paper. (LLM, conf=0.91)

  cites [82] Makomo, 2020, Real Time Application for Automatic Object and 3D Position Detection and Sorting with Robotic Manipulator, Sak. Univ. J. Sci. source
• ?Not checked — no full text of the sourcecites [83] Hermansson, 2021, Quasi-static path optimization for industrial robots with dress packs, Robot. Comput. Integr. Manuf. source
• ?Not checked — no full text of the sourcecites [84] Nguyen, 2021, Hybrid statistical modelling of the frequency response function of industrial robots, Robot. Comput. Integr. Manuf. source

In the paper

“Although the proposed environment resulted in the simple and primitive actions of reaching and picking, it was useful for suction and debris removal in a real surgical setting.”

What the sources say

• Partly supported

  The Discussion and Conclusion says the environments produce simple reaching and picking primitives and demonstrate their utility through suctioning and debris removal. But the Suction and Debris Removal section describes a simulated abdomen with fake blood, not an actual surgical setting; the paper calls it a “realistic surgical setting.” (LLM, conf=0.88)

  cites [63] Richter, F., Orosco, R.K., and Yip, M.C. (2019). Open-Sourced Reinforcement Learning Environments for Surgical Robotics. arXiv. sourceExperimental — accuracy not yet measured

In the paper

“Experiments proved that shared control movements were more accurate, efficient, and less complicated than transfer tasks using BMI alone.”

What the sources say

• Supported

  The Background (page unavailable) reports that shared control improved object transfer for two participants with tetraplegia, lowered perceived task difficulty, and produced more stable and efficient trajectories. It also describes the system as combining BMI control with vision-guided assistance, supporting the comparison with BMI control alone. (LLM, conf=0.91)

  cites [66] Downey, 2016, Blending of brain-machine interface and vision-guided autonomous robotics improves neuroprosthetic arm performance during grasping, J. Neuroeng. Rehabil. source

In the paper

“The patch-based density forecasting networks (PDFNs) directly forecast crowd density maps of future frames instead of trajectories of each moving person in the crowd.”

What the sources say

• Supported

  The Figure 2 caption (Related Work, p. 3) says PDFN forecasts patch-based density dynamics and reconstructs future crowd density maps. The Training Setup (p. 4) explicitly says PDFN-D does so without tracking each detected individual, supporting the contrast with forecasting individual trajectories. (LLM, conf=0.94)

  cites [45] Minoura, 2021, Crowd Density Forecasting by Modeling Patch-Based Dynamics, IEEE Robot. Autom. Lett. source

In the paper

“A flexible transoral robot with a teleoperated configuration is proposed to address the surgeons' risks during the face-to-face COVID-19 swab sampling.”

What the sources say

• Supported

  The Discussion states that the authors propose a flexible transoral robot with a teleoperated configuration to address surgeons’ infection risks during face-to-face COVID-19 swab sampling. The Abstract states the same purpose. The supplied passages do not give page numbers. (LLM, conf=0.95)

  cites [77] Li, 2021, A Flexible Transoral Robot Towards COVID-19 Swab Sampling, Front. Robot. AI source

In the paper

“Proposed patch-based models, PDFN-S and PDFN-ST, outperformed baselines on all the datasets.PDFN-ST successfully forecasted dynamics of individuals, a small group, and a crowd.”

What the sources say

• Partly supported

  The Results (p. 8) say that PDFN outperformed baselines on all evaluated datasets and forecast the dynamics of individuals, a small group, and a crowd. But the Training Setup (p. 4) identifies the tested variants as PDFN-C and PDFN-D, not PDFN-S and PDFN-ST, so the results are not supported for the named models. (LLM, conf=0.88)

  cites [45] Minoura, 2021, Crowd Density Forecasting by Modeling Patch-Based Dynamics, IEEE Robot. Autom. Lett. sourceExperimental — accuracy not yet measured

In the paper

“This robotic system can detect various objects, regardless of their position and orientation, achieving an average success rate of more than 90% in less than 5 min of training time”

What the sources say

• Supported

  Split into 2 atoms — 2 confirmed, 0 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.

  cites [35] Verbelen, 2020, Learning robots to grasp by demonstration, Robot. Auton. Syst. source

In the paper

“The survey results show that the most promising solutions for such a task are RGB-D sensors and CNN-based algorithms for object recognition, and a combination of suction-based and typical two-finger grippers for grasping different objects”

What the sources say

• Supported

  Section 2.4 says RGB-D images were often used for item detection and that CNN-based recognition methods showed good performance. Section 2.2 describes suction plus two-finger grippers as a common configuration adopted by winning teams, supporting the citing sentence’s summary of promising approaches. The passages provide this support in the context of competition systems, rather than as a universal ranking of all bin-picking methods. (LLM, conf=0.87)

  cites [36] Fujita, 2020, What are the important technologies for bin picking? Technology analysis of robots in competitions based on a set of performance metrics, Adv. Robot. source

In the paper

“The accuracy rate of detecting defective and non-defective objects is successfully improved, increasing the training dataset to up to 400 images of defective and non-defective objects.”

What the sources say

• Partly supported

  The Result Analysis section reports that accuracy rose as the training share of the dataset increased, from 78.83% at 70% training to 85.5% at 90% training. It also says the dataset contained 400 images of defective and intact cubes. The 400 images were the total dataset, however, not the number used for training; the largest reported training share was 90%. (LLM, conf=0.88)

  cites [39] Chen, 2020, Object Sorting using Faster R-CNN, Int. J. Artif. Intell. Appl. sourceExperimental — accuracy not yet measured
• ?Not checked — no full text of the sourcecites [56] Albinali, H., and Alzahrani, F.A. (2021, January 30–31). Faster R-CNN for detecting regions in human-annotated micrograph images. Proceedings of the 2021 International Conference of Women in Data Science at Taif University (WiDSTaif), Taif, Saudi Arabia. source
• Partly supported

  Section 3.3 (Experimental Results; page not provided) reports that Faster R-CNN had higher detection accuracy than R-CNN and Fast R-CNN on three datasets. It does not report detecting defective versus non-defective symmetric objects or improving accuracy by increasing a training set to 400 images. (LLM, conf=0.86)

  cites [57] Li, 2021, Analysis of Object Detection Performance Based on Faster R-CNN, J. Phys. Conf. Ser. sourceExperimental — accuracy not yet measured

In the paper

“Moreover, due to favourable conditions (advances in AI, sensing technologies, and computer vision), collaborative industrial robots have become significantly smarter, showing the potential of reliable and secure cooperation, and increasing the productivity and efficiency of the involved processes [15].”

What the sources say

• Partly supported

  Split into 2 atoms — 0 confirmed, 2 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.

  cites [15] Galin, 2019, Automation and robotics in the context of Industry 4.0: The shift to collaborative robots, IOP Conf. Ser. Mater. Sci. Eng. sourceExperimental — accuracy not yet measured

In the paper

“Experimental results showed better performance of the 3-Sigma rule in terms of precision percentage (mean value of 99.9%) and miss rate (mean value of 10%) concerning the Hampel identifier.”

What the sources say

• ?Not checked — no full text of the sourcecites [24] Tannous, 2020, Haptic-based touch detection for collaborative robots in welding applications, Robot. Comput. Integr. Manuf. source
• ?Could not verify

  The Data description presents a raw dataset from 15 welding tests, and Value of the data says it could be used to develop collision-detection algorithms. Neither section reports a comparison of the 3-Sigma rule with the Hampel identifier. Searches for those methods and for the stated 99.9% precision and 10% miss rate found no matching results in our copy. (LLM, conf=0.76)

  cites [25] Tannous, 2020, Load cell torques and force data collection during tele-operated robotic gas tungsten arc welding in presence of collisions, Data Br. sourceExperimental — accuracy not yet measured

In the paper

“The smooth processing strategy improves optimisation efficiency, ensuring minimal stiffness loss.”

What the sources say

• Supported

  Section 5.2 states that smooth processing increased configuration-optimization efficiency and that stiffness loss after smoothing was less than 0.409% in the reported comparison. This supports the claim’s qualitative description of improved efficiency with minimal stiffness loss. (LLM, conf=0.94)

  cites [85] Jiao, J., Tian, W., Zhang, L., Li, B., Hu, J., Li, Y., Li, D., and Zhang, J. (2020). Variable stiffness identification and configuration optimization of industrial robots for machining tasks. Res. Sq. source

In the paper

“The FIRM presented in this paper outlined the ability to classify industrial robot capabilities and match them to specific characteristics of foodstuffs and requirements for their processing based on four steps that navigate eight tasks.”

What the sources say

• Supported

  The Conclusions section states this claim directly: FIRM classifies industrial robot capabilities and matches them to foodstuff characteristics and processing requirements through four steps and eight tasks. (LLM, conf=0.95)

  cites [102] Bader, 2020, A methodology for the selection of industrial robots in food handling, Innov. Food Sci. Emerg. Technol. source

In the paper

“Reducing the number of repetitive jobs by replacing them with robots is not replacing jobs but paving the way for more intelligent jobs.”

What the sources say

• Supported

  The paper’s Conclusions state the attributed point almost verbatim: replacing repetitive jobs with robots is presented as paving the way for more intelligent jobs. (LLM, conf=0.95)

  cites [98] Grobbelaar, 2021, Analyzing human robotic interaction in the food industry, J. Phys. Conf. Ser. source

In the paper

“This work also identified many factors that should lay the groundwork for future research in the application of industrial robots within food manufacturing.”

What the sources say

• Supported

  The Conclusions explicitly state that the work identified factors laying the groundwork for future research on industrial robots in food manufacturing. The passage then gives examples, including bespoke grippers, hygiene, and operator training. (LLM, conf=0.95)

  cites [102] Bader, 2020, A methodology for the selection of industrial robots in food handling, Innov. Food Sci. Emerg. Technol. source

In the paper

“Transferring repetitive and dangerous tasks that humans are increasingly reluctant to perform to robots means that automation can help address the labour and skills crisis, and make the construction industry more attractive [110,111].”

What the sources say

• ?Not checked — no full text of the sourcecites [110] Aparicio, 2020, Robotics in construction: Framework and future directions, Int. J. High-Rise Build.
• Partly supported

  The Introduction (page not provided) describes construction tasks as boring, repetitive, and hazardous, identifies low attractiveness as an industry problem, and calls automation promising. It does not say workers are increasingly reluctant to do those tasks or that transferring them to robots will address a labour and skills crisis or make the industry more attractive. (LLM, conf=0.85)

  cites [111] Follini, C., Magnago, V., Freitag, K., Terzer, M., Marcher, C., Riedl, M., Giusti, A., and Matt, D.T. (2021). Bim-integrated collaborative robotics for application in building construction and maintenance. Robotics, 10. sourceExperimental — accuracy not yet measured

In the paper

“Technical and work-culture factors include an untrained workforce; unproven effectiveness and immature technology; and the current work culture and aversion to change [108].”

What the sources say

• Supported

  The Factors and Themes section explicitly groups an untrained workforce, unproved effectiveness/immature technology, and current work culture/aversion to change under “Technical and workculture factors.” Section 6.3 discusses the same factors as barriers to adopting robotics in construction. (LLM, conf=0.95)

  cites [108] Oyedele, 2019, Robotics and automated systems in construction: Understanding industry-specific challenges for adoption, J. Build. Eng. source

In the paper

“However, the trust in human-robotic interaction appears to be underdeveloped.”

What the sources say

• Supported

  The Conclusions section directly states that trust between humans and robots in human–robot interaction seems underdeveloped. The claim closely paraphrases that statement. (LLM, conf=0.95)

  cites [98] Grobbelaar, 2021, Analyzing human robotic interaction in the food industry, J. Phys. Conf. Ser. source

In the paper

“This allows the machine to perform weeding and watering while maintaining the moisture content of the deep soil at 80 ± 10% and an average weeding rate of 90%.”

What the sources say

• Supported

  The indexed paper’s Abstract (page not specified) states that the machine weeds and waters while maintaining deep-soil moisture at 80 ± 10% and achieving an average weeding rate of 90%. This matches the attributed claim. (LLM, conf=0.95)

  cites [105] Chang, C.-L., and Lin, K.-M. (2018). Smart Agricultural Machine with a Computer Vision-Based Weeding and Variable-Rate Irrigation Scheme. Robotics, 7. source

In the paper

“The system can classify plants and weeds in real time with an average classification rate of 90% or higher.”

What the sources say

• Partly supported

  Section 2.1.1 describes the system’s weed/plant classification method, and Section 3.2 describes real-time observation of crops and weeds. The retrieved main-text passages do not establish an average classification rate of 90% or higher; that figure appears only in the Abstract, which is excluded as evidence under the stated rubric. (LLM, conf=0.73)

  cites [105] Chang, C.-L., and Lin, K.-M. (2018). Smart Agricultural Machine with a Computer Vision-Based Weeding and Variable-Rate Irrigation Scheme. Robotics, 7. sourceExperimental — accuracy not yet measured

In the paper

“The proposed approach made the robot learn the task execution and compensate for the task uncertainties.”

What the sources say

• Supported

  The Conclusions state that validation experiments showed the robot learning the assembly task while compensating for task uncertainties. The Paper contribution section also describes learning a nominal task and re-optimizing it to address those uncertainties. (LLM, conf=0.95)

  cites [90] Roveda, 2021, Human–robot collaboration in sensorless assembly task learning enhanced by uncertainties adaptation via Bayesian Optimization, Rob. Auton. Syst. source

In the paper

“The task's execution time was reduced by 13.1% regarding the robot's default planner and 19.6% concerning the minimum jerk smooth collaboration planner.”

What the sources say

• Supported

  The Conclusions explicitly report a 13.1% reduction in task execution time relative to the robot’s default planner and a 19.6% reduction relative to the minimum-jerk smooth collaborative planner. The Experiment section identifies the three planners compared in the pick-and-pass task. (LLM, conf=0.95)

  cites [89] Rojas, 2021, Combining safety and speed in collaborative assembly systems—An approach to time optimal trajectories for collaborative robots, Procedia CIRP source

In the paper

“Effective robotic production still requires the communication and management of progressively improving materials and building systems.”

What the sources say

• Partly supported

  The Conclusion and Outlook says efficient robotized production requires incremental advancement in communication and control that are aware of materials and building systems. The claim shifts that advancement to the materials and building systems themselves, which the passage does not support. (LLM, conf=0.82)

  cites [117] Bodea, S., Mindermann, P., Gresser, G.T., and Menges, A. (2021). Additive Manufacturing of Large Coreless Filament Wound Composite Elements for Building Construction. 3D Print. Addit. Manuf., ahead of print. sourceExperimental — accuracy not yet measured

In the paper

“The emergence of robotics in business is widely seen across the world.”

What the sources say

• Supported

  The Conclusions state almost exactly that the emergence of robotics in business is widely seen across the world. The claim omits the paper’s subsequent observation about underdeveloped trust, but does not contradict it. (LLM, conf=0.95)

  cites [98] Grobbelaar, 2021, Analyzing human robotic interaction in the food industry, J. Phys. Conf. Ser. source

In the paper

“In particular, the HMM + BO methodology shows an assembly task success rate of 93%, while the HMM algorithm shows a success rate of only 19%.”

What the sources say

• Supported

  Section 6.4 (HMM+BO vs. HMM) reports a 93% successful assembly-task execution rate for HMM+BO and 19% for HMM alone, based on 150 repetitions per method. Section 1.3 (Paper contribution) also states both rates explicitly. (LLM, conf=0.95)

  cites [90] Roveda, 2021, Human–robot collaboration in sensorless assembly task learning enhanced by uncertainties adaptation via Bayesian Optimization, Rob. Auton. Syst. source

In the paper

“Robotics is applied in food manufacture, packaging, delivery, and cookery (cake decoration) [98].”

What the sources say

• Supported

  The Abstract says robots are used in food production, packaging, and delivery. Section 3.6, “Bakery,” describes robotic cake decoration using an arm that pipes icing onto cakes. (LLM, conf=0.94)

  cites [98] Grobbelaar, 2021, Analyzing human robotic interaction in the food industry, J. Phys. Conf. Ser. source

In the paper

“According to the machining results of a cylinder head of a vehicle engine, the milling quality was improved obviously after the configuration optimisation, and the validity of these methods are verified.”

What the sources say

• Supported

  The Machining Experiment section reports milling an automobile-engine cylinder head and finds that surface roughness fell from Ra 2.356 to Ra 0.597 after configuration optimization. The Conclusions explicitly state that milling quality improved and that the methods were verified. (LLM, conf=0.95)

  cites [85] Jiao, J., Tian, W., Zhang, L., Li, B., Hu, J., Li, Y., Li, D., and Zhang, J. (2020). Variable stiffness identification and configuration optimization of industrial robots for machining tasks. Res. Sq. source

In the paper

“Kinect could distinguish colour correctly, and the robot could accurately navigate to the detected object.”

What the sources say

• Partly supported

  The Abstract (page not provided) describes using a Kinect camera to locate objects and calculate a path for the robot to grasp them. It does not report that the Kinect distinguished colours correctly or that the robot navigated to detected objects accurately. (LLM, conf=0.82)

  cites [82] Makomo, 2020, Real Time Application for Automatic Object and 3D Position Detection and Sorting with Robotic Manipulator, Sak. Univ. J. Sci. sourceExperimental — accuracy not yet measured

In the paper

“The results of this review revealed four directions of required advancement in robotics: development of intelligent companions; improved implementation of AI-based solutions; robot-oriented design of objects; and psychological solutions for robot-human collaboration.”

In the paper

“It is based on the approach that robots must limit humans in their workplace by creating closed robot cells in which human activity is unacceptable; if a human must enter the robot's workspace, the robot must be stopped.”

In the paper

“In 2020 the total number of industrial robots operating in factories globally reached 2.7 million.”

What the sources say

• Not checked yetcites [2] (2021, April 07). IFR Presents World Robotics Report 2020—International Federation of Robotics. Available online: https://ifr.org/ifr-press-releases/news/record-2.7-million-robots-work-in-factories-around-the-globe.

In the paper

“According to [13], the definition of cobot was first used in a 1999 US patent [14] and was intended for “an apparatus and method for direct physical integration between a person and a general-purpose manipulator controlled by a computer.””

What the sources say

• Not checked yetcites [13] (2021, April 08). A Brief History of Collaborative Robots|Material Handling and Logistics. Available online: https://www.mhlnews.com/technology-automation/article/21124077/a-brief-history-of-collaborative-robots.
• ?Not matched

  Couldn’t be matched to a paper in Crossref, so it can’t be checked.

  cites [14] Colgate, J.E., and Peshkin, M.A. (1999). Cobots. (5,952,796), U.S. Patent.

In the paper

“In industrial robotics, five typical levels of human-robot cooperation are defined (Figure 2): (i) no collaboration; (ii) coexistence; (iii) synchronisation; (iv) cooperation; (v) collaboration [5].”

What the sources say

• ?Not checked — no full text of the sourcecites [5] Olivares-Alarcos, A., Foix, S., and Alenyà, G. (2019). On inferring intentions in shared tasks for industrial collaborative robots. Electronics, 8. source

In the paper

“Moreover, the issue of implementing an industrial robot remains complicated by its interdisciplinary nature: proper organisation of the work cycle is the object of manufacturing management sciences; the design of grippers and related equipment lies within the field of mechanical engineering; and the integration of all devices into a united system, sensor data analysis and whole system control are”

In the paper

“Evaluation of the use of the robots based on their number and real implementation price determined that implementation of robots positively affects productivity, which results in a positive impact for the most vulnerable workers in society, i.e., women, parttime workers, high-school graduates, and aged persons.”

What the sources say

• ?Not checked — no full text of the sourcecites [4] Dekle, 2020, Robots and industrial labor: Evidence from Japan, J. Jpn. Int. Econ. source

In the paper

“The classic strategy is well suited to robotisation of mass production processes in various fields, and its main advantages are clear requirements for work process organisation, robotic cell design, and installation; the availability of a large variety of standard equipment and typical partial solutions; and higher productivity and reliability compared to the cases where human workers perform the”

In the paper

“As a result, the robotisation of even a relatively simple task becomes a complex solution requiring a systemic approach.”

In the paper

“In [11], a perspective non-linear model-based predictive control method for robotic manipulators, which minimises the settling time and position overshoot of each joint, is provided.”

What the sources say

• ?Not checked — no full text of the sourcecites [11] Elsisi, 2021, Effective Nonlinear Model Predictive Control Scheme Tuned by Improved NN for Robotic Manipulators, IEEE Access source

In the paper

“Each robotisation task is unique in its own way.”

In the paper

“The main disadvantages are insufficient flexibility, unsuitability for unique production, and high economic costs when it is necessary to adapt the existing robotic cell to a new product or process.”

In the paper

“This is based on an opposing approach, and states that robots and humans can work in one workplace and collaborate.”

In the paper

“The first lightweight cobot, LBR3, designed by a German robotics company, was introduced in 2004 [13].”

What the sources say

• Not checked yetcites [13] (2021, April 08). A Brief History of Collaborative Robots|Material Handling and Logistics. Available online: https://www.mhlnews.com/technology-automation/article/21124077/a-brief-history-of-collaborative-robots.

In the paper

“According to the International Federation of Robotics (IRF) [2], 373,000 industrial robots were sold globally in 2019.”

What the sources say

• Not checked yetcites [2] (2021, April 07). IFR Presents World Robotics Report 2020—International Federation of Robotics. Available online: https://ifr.org/ifr-press-releases/news/record-2.7-million-robots-work-in-factories-around-the-globe.

In the paper

“According to one of the biggest scientific databases, ScienceDirect [3], more than 4500 scientific papers were published in 2019 using the term “Industrial robot” as a keyword and, in 2020, the number of papers with a similar interest and research direction increased to 5300.”

What the sources say

• Not checked yetcites [3] (2021, April 07). ScienceDirect Search Results—Keywords (Industrial Robot). Available online: https://www.sciencedirect.com/search?qs=Industrial%20robot.

In the paper

“The issue of data protection is also becoming more critical due to the latest communication technologies, such as 5G and 6G [18].”

What the sources say

• ?Not checked — no full text of the sourcecites [18] Rao, 2018, Impact of 5G Technologies on Industry 4.0, Wirel. Pers. Commun. source

In the paper

“When a corner is detected, it takes just 0.003 s to output the target point.”

What the sources say

• ?Not checked — no full text of the sourcecites [43] Tripicchio, 2020, A study on picking objects in cluttered environments: Exploiting depth features for a custom low-cost universal jamming gripper, Robot. Comput. Integr. Manuf. source

In the paper

“This can be explained by the fact that experts better understand the overall manufacturing process and are more accustomed to operating with various equipment.”

In the paper

“The surveyed articles were selected according to the direction of the literature review and the indicated criteria (application area, novelty and significance of achievements, reliability, and feasibility of results).”

In the paper

“The use of CAM software also requires highly qualified professionals.As a result, the application of this software to individual installations is economically disadvantageous.”

In the paper

“When using lines, the time required depends significantly on the configuration of the objects, and ranges from 0.02 s when the objects have almost the same depth, to 0.06 s in the worst case when the depth of the tactile objects is greater than the lowest depth but not perceived [43].”

What the sources say

• ?Not checked — no full text of the sourcecites [43] Tripicchio, 2020, A study on picking objects in cluttered environments: Exploiting depth features for a custom low-cost universal jamming gripper, Robot. Comput. Integr. Manuf. source

In the paper

“The presented method achieved identification accuracy of coal and gangue samples of 88.3% and 90.0%, and the average object mass centre coordinate errors in the x and y directions were 2.73% and 2.72%, respectively [42].”

What the sources say

• ?Not checked — no full text of the sourcecites [42] Li, M., Duan, Y., He, X., and Yang, M. (2020). Image positioning and identification method and system for coal and gangue sorting robot. Int. J. Coal Prep. Util., 1–19. source

In the paper

“A personalised deep learning framework can adapt robot perception of children's affective states and engagement to different cultures and individuals.”

What the sources say

• ?Not checked — no full text of the sourcecites [68] Rudovic, 2018, Personalized machine learning for robot perception of affect and engagement in autism therapy, Sci. Robot. source

In the paper

“Because close interactions are the most difficult, it is crucial to consider a number of aspects to ensure a successful collaboration, i.e., a real-time algorithm, “touch” detection and analysis, autonomy, semantic understanding capabilities, and AI-aided anticipation skills.”

In the paper

“This standard defines four main classes of safety requirements for collaborative robots: safety-rated monitored stop; hand-guiding; speed and separation monitoring; and power and force limiting.”

What the sources say

• Not checked yetcites [23] (2021, December 02). ISO—ISO/TS 15066:2016—Robots and Robotic Devices—Collaborative Robots. Available online: https://www.iso.org/standard/62996.html.

In the paper

“they found that the main limitations preventing deep learning in medical robotics are the huge volume of training data required and a relatively long training time.”

What the sources say

• ?Not checked — no full text of the sourcecites [65] Pierson, 2017, Deep learning in robotics: A review of recent research, Adv. Robot. source

In the paper

“Using an Elite EC75 manipulator (Elite Robot, Suzhou, CN, an assembly time of less than 20 s was achieved, ensuring a 100% success rate from 30 attempts when the relative error between the peg and hole was ±4.5 mm, and the clearance between the peg and the hole was 0.18 mm.”

What the sources say

• ?Not checked — no full text of the sourcecites [20] Song, 2021, A peg-in-hole robot assembly system based on Gauss mixture model, Robot. Comput. Integr. Manuf. source

In the paper

“Nevertheless, it is necessary to note that the strict line between these strategies has gradually disappeared due to advances in sensing technologies, artificial intelligence, and computer vision.”

In the paper

“This automatic sorting robot can automatically sort construction and demolition waste ranging in size from 0.05 to 0.5 m.The online recognition accuracy of the developed sorting system reaches almost 100% and ensures operation speed up to 2028 picks/h.”

What the sources say

• ?Not checked — no full text of the sourcecites [41] Xiao, 2020, Development of an automatic sorting robot for construction and demolition waste, Clean Technol. Environ. Policy source

In the paper

“In addition, it is essential to mention that all improvements and advances in robotics can be classified into two main types: universal and application dependent.”

In the paper

“However, the functionality of such software is relatively constrained and does not go beyond the framework of classical tasks, such as welding or milling.”

In the paper

“The main impact of Industry 4.0 and new communication technologies on industrial robots is that their controllers have an increasing number of connections, functions, and protocols to communicate with other “smart” devices.”

In the paper

“Compared to traditional industrial robots, cobots have more user-friendly control features and wider teaching options.”

In the paper

“The obtained results showed that humans and robots could simultaneously work safely in a common area without any physical separation, and significantly reduce time and costs compared with manual operations.”

What the sources say

• ?Not checked — no full text of the sourcecites [19] Usamentiaga, 2020, Symbiotic human–robot collaborative approach for increased productivity and enhanced safety in the aerospace manufacturing industry, Int. J. Adv. Manuf. Technol. source

In the paper

“Nevertheless, any kind of path planning requires information about the initial robot position.”

In the paper

“A large number of reliable solutions have been tested in the industrial environment for the first trend, in contrast to the second and third cases, which are currently being developed.”

In the paper

“Robotic technologies in dentistry can be used for maxillofacial surgery [70], tooth preparation [71], testing of toothbrushes [72], root canal treatment and plaque removal [73], orthodontics and jaw movement [74], tooth arrangement for full dentures [75], X-ray imaging radiography [76], swab sampling [77], etc.”

What the sources say

• ?Not checked — no full text of the sourcecites [69] Grischke, 2020, Dentronics: Towards robotics and artificial intelligence in dentistry, Dent. Mater. source

In the paper

“Therefore, both human and robot communication or interaction can be divided into two main categories: remote interaction and exact interaction.”

In the paper

“Achieved an average agreement of ~60% with human experts to estimate effect and engagement.”

What the sources say

• ?Not checked — no full text of the sourcecites [68] Rudovic, 2018, Personalized machine learning for robot perception of affect and engagement in autism therapy, Sci. Robot. source

In the paper

“The fourth industrial revolution-Industry 4.0-significantly fostered the development of cobot's technologies, because the concept fitted well with Industry 4.0 content, allowing human-robot collaboration to be realised and being suitable for flexible manufacturing systems.”

In the paper

“In 2008, the Danish manufacturer Universal Robots released the UR5, a cobot that could safely operate alongside the employees, eliminating the need for safety caging or fencing (Figure 3b).”

What the sources say

• Not checked yetcites [13] (2021, April 08). A Brief History of Collaborative Robots|Material Handling and Logistics. Available online: https://www.mhlnews.com/technology-automation/article/21124077/a-brief-history-of-collaborative-robots.

In the paper

“The process known as robotic navigation aims to achieve accurate positioning and avoiding obstacles in the pathway.It is essential to satisfy constraints such as limited operating space, distance, energy, and time [78].”

What the sources say

• ?Not checked — no full text of the sourcecites [78] Jose, 2016, Task allocation and collision-free path planning of centralized multi-robots system for industrial plant inspection using heuristic methods, Rob. Auton. Syst. source

In the paper

“It can be seen that robots are still not very popular in this area, and technological and phycological/ethical factors can explain this.”

In the paper

“Nevertheless, employee attitudes depend on their practical experience: it was noticed that experts felt more confident than beginners.”

What the sources say

• ?Not checked — no full text of the sourcecites [19] Usamentiaga, 2020, Symbiotic human–robot collaborative approach for increased productivity and enhanced safety in the aerospace manufacturing industry, Int. J. Adv. Manuf. Technol. source

In the paper

“The path trajectory formation process consists of these four separate modules: perception, when the robot receives the necessary information from the sensors; localisation, when the robot aims to control its position in the environment; path planning; and motion control [79].”

What the sources say

• ?Not checked — no full text of the sourcecites [79] Das, 2020, Multi-robot path planning using improved particle swarm optimization algorithm through novel evolutionary operators, Appl. Soft Comput. J. source

In the paper

“To overcome the limitations caused by the lack of real-time path planning features in robot controllers, additional external controllers and real-time communication with the manipulator is required.”

In the paper

“Experiments performed on solid waste image analysis resulted in a mean average precision value of 49.1%.”

What the sources say

• ?Not checked — no full text of the sourcecites [40] Yu, 2020, A novel detection fusion network for solid waste sorting, Int. J. Adv. Robot. Syst. source

In the paper

“As an alternative to CAM software, methods based on the copying movements of highly skilled specialists using commercially available equipment, such as MIMIC from Nordbo Robotics (Antvorskov, Denmark), may be used.”

In the paper

“Although the food industry is ranked fourth in terms of the mostautomated sectors, robotic devices capable of processing nutrients of different shapes and materials are in high demand.”

In the paper

“The total global value of the construction industry is forecast to grow by 85% to USD 15.5 trillion by 2030 [109].”

What the sources say

• Not checked yetcites [109] Robinson, G. (2016). Global Construction Market to Grow $8 Trillion by 2030: Driven by China, US and India, Global Construction Perspectives and Oxford Economics.

In the paper

“The system outperforms the operator performing the same task with magnified visual feedback regarding both completion time and the number of successful insertions.”

In the paper

“The methodology reduced the average number of iterations and calibration times required to determine the optimal GPR model hyperparameters by 50.3% and 31.3%, respectively.”

In the paper

“Applications of robotic grippers in food, agricultural, and bio-system engineering were summarised in detail.”

What the sources say

• ?Not checked — no full text of the sourcecites [104] Zhang, 2020, State-of-the-art robotic grippers, grasping and control strategies, as well as their applications in agricultural robots: A review, Comput. Electron. Agric. source

In the paper

“Robots are used in planting, seedling identification, and sorting.”

In the paper

“Artificial intelligence-enabled robotic applications are entering the restaurant industry in the food processing and guest service operations.”

In the paper

“In the process of experimental verification, task-level planning can maintain the same accuracy as that of the traditional method but saves time when facing more complex tasks.”

What the sources say

• ?Not checked — no full text of the sourcecites [86] Ding, 2020, BIM-based task-level planning for robotic brick assembly through image-based 3D modeling, Adv. Eng. Inform. source

In the paper

“The simplest visual system was used to follow a simplified approach, which can be controlled directly by a robot controller.”

What the sources say

• ?Not checked — no full text of the sourcecites [114] Gautam, M., Fagerlund, H., Greicevci, B., Christophe, F., and Havula, J. (2020, January 27–28). Collaborative Robotics in Construction: A Test Case on Screwing Gypsum Boards on Ceiling. Proceedings of the 2020 5th International Conference on Green Technology and Sustainable Development, Ho Chi Minh City, Vietnam. source

In the paper

“An industrial robot with only three joints is used, and the solutions of joint angles for the tool orientations are not proposed, which is essential for printing the freeform surface.”

What the sources say

• ?Not checked — no full text of the sourcecites [91] Fu, 2020, A postprocessing and path optimization based on nonlinear error for multijoint industrial robot-based 3D printing, Int. J. Adv. Robot. Syst. source

In the paper

“Drones and autonomous ground vehicles are used for crop monitoring and condition assessment.”

In the paper

“The agriculture robot market size is expected to reach USD 16,640.4 billion by 2026; however, specific robots, rather than industrial robots, will occupy the majority of the market.”

In the paper

“Furthermore, bypassing limitations in one area often ensures advances in robotics in other sectors.”