{"title":"ISMCR2022 - Organizing Committee","authors":"","doi":"10.1109/ismcr56534.2022.9950567","DOIUrl":"https://doi.org/10.1109/ismcr56534.2022.9950567","url":null,"abstract":"","PeriodicalId":359153,"journal":{"name":"2022 International Symposium on Measurement and Control in Robotics (ISMCR)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134276058","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Self-Supervised Occlusion Detection and Avoidance using Differentiable Rendering","authors":"M. Szántó, Marton Szemenyei","doi":"10.1109/ISMCR56534.2022.9950574","DOIUrl":"https://doi.org/10.1109/ISMCR56534.2022.9950574","url":null,"abstract":"Deep Learning-based computer vision methods have achieved state-of-the-art performance in the last decade, prompting a renaissance in the field of Artificial Intelligence (AI). Still, despite recent successes, many challenges remain including the robustness of these solutions to disturbances of the input, such as occlusion. While some solutions exist for neural network-based object detection under partial occlusions, these methods still implement the object detector as a passive observer in the scene. We argue, however, that an active object detector agent may be able to achieve better results by changing its own position to resolve occlusion, when possible. In this paper, an OpenAI Gym-compatible virtual environment is presented that enables the creation of realistic occlusion datasets via differentiable rendering. A trained neural network is also presented that predicts the occlusion mask and the optimal camera movement via self-supervised learning in the environment. Our experiments presented in this paper show that the neural network model is able to outperform the gradient-based optimization, and efficiently avoid occlusion in simulated scenes containing multiple objects.","PeriodicalId":359153,"journal":{"name":"2022 International Symposium on Measurement and Control in Robotics (ISMCR)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124629394","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Monaliza de Oliveira Almeida, Carlos Henrique Simões de Sousa, José Guilherme Pereira Peixoto
{"title":"The Importance of Using Simulators in Dosimetry for Radiation Protection","authors":"Monaliza de Oliveira Almeida, Carlos Henrique Simões de Sousa, José Guilherme Pereira Peixoto","doi":"10.1109/ISMCR56534.2022.9950564","DOIUrl":"https://doi.org/10.1109/ISMCR56534.2022.9950564","url":null,"abstract":"The main objective of radiological protection dosimetry is to evaluate the absorbed dose in sensitive organs and tissues of the human body by internal or external sources of radiation (ICRP 103, 2007). Simulators are physical or computational models used to simulate the transport of ionizing radiation, and its interactions in the tissues of the human body and to evaluate energy deposition in regions of interest. The Monte Carlo method is applied to reproduce a statistical process similar to the interaction of nuclear particles with human tissues. The objective of this work is, through literary research, to compare computational Simulators with physical Simulators, and to show the importance and evolution of the use of computational Simulators in the dosimetry of radiological protection. Physical Simulators, especially anthropomorphic ones, are very expensive and limited, besides being difficult to position (AP/PA/PERFIL). Computer simulators do not have radiation emissions, which protects researchers and ensures that there is no variation of the simulated radiation beam. To reduce uncertainty in dose calculations caused by anatomical variations, the scientific community has developed several computational Simulators with modified ICRP standard reference values about body mass, height, positioning, size and position of organs and structures, etc.","PeriodicalId":359153,"journal":{"name":"2022 International Symposium on Measurement and Control in Robotics (ISMCR)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117333546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Development of an environment mapping robot using polygonal map representation","authors":"András Izsó, I. Harmati","doi":"10.1109/ISMCR56534.2022.9950588","DOIUrl":"https://doi.org/10.1109/ISMCR56534.2022.9950588","url":null,"abstract":"The simultaneous localization and mapping problem nowadays has many implementations for single robot systems. The current challenge is to extend these algorithms to work efficiently with a multi-agent setup as well. One of the arising problems is the limited bandwidth for communication between the agents. The industry standard grid-map based representation is a very verbose one, thus making data exchange between the agents more challenging. This paper proposes an outline of a new, polygon-based map representation and presents our results so far. We recognize the importance of testing such a new architecture on a physical system. Therefore, a robotic system was designed and implemented, which is cost effective enough for our research group to be able to afford multiple instances of it, even on a tight budget and makes data gathering and exchange possible between the agents. In this paper we describe our map representation, the steps of the map building, the important design decisions of the implemented system and present the achieved results.","PeriodicalId":359153,"journal":{"name":"2022 International Symposium on Measurement and Control in Robotics (ISMCR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131296579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Efficient Neural Network Pruning Using Model-Based Reinforcement Learning","authors":"Blanka Bencsik, Marton Szemenyei","doi":"10.1109/ISMCR56534.2022.9950598","DOIUrl":"https://doi.org/10.1109/ISMCR56534.2022.9950598","url":null,"abstract":"Model compression plays a vital role in the deployment of neural networks (NNs) in resource-constrained devices. Rule-based conventional NN pruning is sub-optimal due to the enormous design space that cannot be examined entirely by hand. To overcome this issue, automated NN pruning leverages a reinforcement learning agent to automatically find the best combination of parameters to be removed from a given model. We propose a novel RL-based automated pruning algorithm that, unlike existing RL-based methods, determines the environmental variables using a State Predictor Network as a simulated environment instead of validating the pruned model in run time. Testing our method on the YOLOv4 detector, a model with 49 % sparsity was produced with 7.2 % higher mAP. This result outperforms our handcrafted pruning methods for YOLOv4 by 2.3 % mAP and 17.1 % sparsity. Regarding total development time, our method is 146.2 times faster than the state-of-the-art PuRL method using NVIDIA Titan X GPU. The implementation of the proposed solution is available at: https://github.com/bencsikb/Efficient_RLPruning","PeriodicalId":359153,"journal":{"name":"2022 International Symposium on Measurement and Control in Robotics (ISMCR)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132268676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"HISTORY OF ISMCR and TC17 Meetings","authors":"","doi":"10.1109/ismcr56534.2022.9950566","DOIUrl":"https://doi.org/10.1109/ismcr56534.2022.9950566","url":null,"abstract":"","PeriodicalId":359153,"journal":{"name":"2022 International Symposium on Measurement and Control in Robotics (ISMCR)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132224458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
F. Kato, T. Adachi, T. Handa, Kaito Kamishima, H. Iwata
{"title":"Palpation Robot System - Reproduction Method by Deep Neural Network of Skin Palpation Judgment Focusing on Softness Classification-","authors":"F. Kato, T. Adachi, T. Handa, Kaito Kamishima, H. Iwata","doi":"10.1109/ISMCR56534.2022.9950593","DOIUrl":"https://doi.org/10.1109/ISMCR56534.2022.9950593","url":null,"abstract":"In recent years, the spread of infectious diseases, such as COVID-19, has increased the need for medical examinations to avoid contact between doctors and patients. Most treatments, especially dermatology, require palpation, and its impact is significant. In this study, we aimed to reproduce the judgment of the softness and surface textures of diseased parts, which is important to dermatologists for determining the condition, using a simple robot device. Five levels of softness and three types of surface textures labeled with 14 types of materials were obtained from interviews with dermatologists. To acquire a haptic response from materials during pushing, 1) a single-rod probe with a haptic sensor using a linear actuator and 2) a dual-rod type configuration to obtain vibration propagation was constructed. Frequency-analyzed images were produced from the obtained waveforms of force and acceleration. A total of 343 images from 13 materials were used for transfer learning and were classified using AlexNet. The classification accuracy of the single-rod probe was 93.0%, and that of the dual-probe configuration was 95.2%. The classification accuracy was improved using the dual probe configuration than the single one; the softness classification accuracy was improved from 93.8% (single-rod) to 95.7% (dual-rod configuration). The surface texture classification accuracy was improved from 91.9% (single-rod) to 92.8% (dual-rod configuration), respectively. Therefore, the proposed method enables the reproduction of the judgment of five-level softness and three types of surface texture judgment by dermatologists.","PeriodicalId":359153,"journal":{"name":"2022 International Symposium on Measurement and Control in Robotics (ISMCR)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134173515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kaito Kamishima, F. Kato, Yukiko Iwasaki, Nonoka Nishida, H. Iwata
{"title":"Study on Attention Distribution for Supernumerary Limbs in Dual-task -Effectiveness of Vibration Feedback for Limb Posture","authors":"Kaito Kamishima, F. Kato, Yukiko Iwasaki, Nonoka Nishida, H. Iwata","doi":"10.1109/ISMCR56534.2022.9950577","DOIUrl":"https://doi.org/10.1109/ISMCR56534.2022.9950577","url":null,"abstract":"When using a supernumerary limb, it is necessary to pay appropriate attention to the supernumerary limb and recognize its state. In this study, we verified whether the posture of a supernumerary limb removed from a human and placed in an environment could be perceived from the tactile feedback in a dual-task. Then, we examined the effect of perceivability on dual-task performance. In the former verification, participants were asked to answer the position of a randomly stopped supernumerary limb while pouring a prescribed volume of water with their natural bodies. The latter was examined with 2 kinds of dual-tasks. Dual-task A required the tasks on the natural body and the supernumerary limb sides to have a common perceptual modality. Dual-task B did not require the tasks on the natural body and supernumerary limb sides to have a common perceptual modality. Thus, supernumerary limb location identification accuracy was as good in dual-task conditions as in single-task conditions. In addition, task performance in dual-task B was improved by the presence of tactile feedback.","PeriodicalId":359153,"journal":{"name":"2022 International Symposium on Measurement and Control in Robotics (ISMCR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127715714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"The International Symposium on Measurement and Control in Robotics - Program","authors":"","doi":"10.1109/ismcr56534.2022.9950571","DOIUrl":"https://doi.org/10.1109/ismcr56534.2022.9950571","url":null,"abstract":"","PeriodicalId":359153,"journal":{"name":"2022 International Symposium on Measurement and Control in Robotics (ISMCR)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116923526","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}