Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9216951
F. Parisi, A. M. Mangini, M. P. Fanti
Data-driven knowledge extraction is becoming one the greatest source of information to study and manage complex systems. Today, new challenges can be provided thanks to Information and Communication Technologies and IoT paradigm that are allowing big mass of data to be stored, processed and analyzed. In this paper an insight on data driven knowledge extraction potentiality in the field of smart construction engineering is given. In particular, the main technologies for supporting the decision-management phase in Architecture, Engineering and Construction Industry (AEC Industry) are analysed. To this aim, such technologies are classified in four fields and the main contributions presented in the related literature are singled out and discussed. Finally, some examples of the current applications in the AEC industry are presented and the gap for future development in this field is enlightened.
{"title":"Enabling Technologies for Smart Construction Engineering: a Review","authors":"F. Parisi, A. M. Mangini, M. P. Fanti","doi":"10.1109/CASE48305.2020.9216951","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216951","url":null,"abstract":"Data-driven knowledge extraction is becoming one the greatest source of information to study and manage complex systems. Today, new challenges can be provided thanks to Information and Communication Technologies and IoT paradigm that are allowing big mass of data to be stored, processed and analyzed. In this paper an insight on data driven knowledge extraction potentiality in the field of smart construction engineering is given. In particular, the main technologies for supporting the decision-management phase in Architecture, Engineering and Construction Industry (AEC Industry) are analysed. To this aim, such technologies are classified in four fields and the main contributions presented in the related literature are singled out and discussed. Finally, some examples of the current applications in the AEC industry are presented and the gap for future development in this field is enlightened.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123504307","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}
Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9217002
Tariku Sinshaw Tamir, Gang Xiong, Hiruy Mulugeta Menkir, Xiuqin Shang, Zhen Shen, Xisong Dong, Xiaoyan Gong
The SCADA system, which means Supervisory Control and Data Acquisition systems, are widely used in automatic management and control of producing and manufacturing processes throughout the world, reducing manpower and improving production efficiency. However, in Ethiopia, the manufacturing sector is at its infant stage and manual systems are mostly applied in existing factories. Therefore, in this paper we design a monitoring system based on existing SCADA system only in English and develops HMI software with GUI representing sub components to enable computerized controlling and monitoring of different parts in factories both in English and Amharic. Simulation results show interactions among sensors, actuators, SCADA hardware and HMI software in the overall system and real time data can be transferred and stored in databases. Finally, it is observed from PI controllers that tanker’s level can reach its steady state value after 0.15 seconds.
{"title":"Developing SCADA Systems to Monitor and Control Liquid and Detergent Factories","authors":"Tariku Sinshaw Tamir, Gang Xiong, Hiruy Mulugeta Menkir, Xiuqin Shang, Zhen Shen, Xisong Dong, Xiaoyan Gong","doi":"10.1109/CASE48305.2020.9217002","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9217002","url":null,"abstract":"The SCADA system, which means Supervisory Control and Data Acquisition systems, are widely used in automatic management and control of producing and manufacturing processes throughout the world, reducing manpower and improving production efficiency. However, in Ethiopia, the manufacturing sector is at its infant stage and manual systems are mostly applied in existing factories. Therefore, in this paper we design a monitoring system based on existing SCADA system only in English and develops HMI software with GUI representing sub components to enable computerized controlling and monitoring of different parts in factories both in English and Amharic. Simulation results show interactions among sensors, actuators, SCADA hardware and HMI software in the overall system and real time data can be transferred and stored in databases. Finally, it is observed from PI controllers that tanker’s level can reach its steady state value after 0.15 seconds.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116477177","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}
Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9216991
Georg Friedrich Schuppe, Jana Tumova
We propose a compositional solution to the strategy synthesis problem for LTL specifications in the cooperative (heterogeneous) multi-agent scenario. A main challenge of the general strategy synthesis approach is the state-space explosion occurring during construction of a global model for agents with different, mutually dependent goals. Given a set of agents and their individual goal specifications represented through a local model and an LTL formula, we compute a compliant set of strategies that fulfill each agents’ goal specification. We avoid the state-space explosion by computing individual solutions for each agent separately and then composing these solutions. During the initial strategy computation, assumptions over the states of other agents not represented in the local model are generated only where needed. These assumptions are resolved during composition of the individual solutions to assure compliance of the computed strategies. The effectiveness of this approach is demonstrated in several simulation case studies and compared to the classical, monolithic approach.
{"title":"Multi-Agent Strategy Synthesis for LTL Specifications through Assumption Composition","authors":"Georg Friedrich Schuppe, Jana Tumova","doi":"10.1109/CASE48305.2020.9216991","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216991","url":null,"abstract":"We propose a compositional solution to the strategy synthesis problem for LTL specifications in the cooperative (heterogeneous) multi-agent scenario. A main challenge of the general strategy synthesis approach is the state-space explosion occurring during construction of a global model for agents with different, mutually dependent goals. Given a set of agents and their individual goal specifications represented through a local model and an LTL formula, we compute a compliant set of strategies that fulfill each agents’ goal specification. We avoid the state-space explosion by computing individual solutions for each agent separately and then composing these solutions. During the initial strategy computation, assumptions over the states of other agents not represented in the local model are generated only where needed. These assumptions are resolved during composition of the individual solutions to assure compliance of the computed strategies. The effectiveness of this approach is demonstrated in several simulation case studies and compared to the classical, monolithic approach.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124389427","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}
Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9216857
Nathan D. Wallace, He Kong, A. Hill, S. Sukkarieh
The planning of long-duration missions for resource-constrained agents is a longstanding challenge not only in field robotics research, but also in the fields of vehicle routing and logistics. To efficiently plan missions over a larger time scale than an agent’s resource capacity natively allows, it is necessary to exploit the availability of recharging stations, where an agent can replenish its spent resources at the cost of time. This paper presents the Orienteering Problem with Replenishment, a novel extension of the orienteering problem, which can fully utilise the existence of recharging stations by not only revisiting such stations, but also intelligently managing the amount of time spent recharging at each stop. By leveraging the above mechanisms for overcoming the resource limitations of the platform, the proposed problem formulation allows for the planning of longer term missions. A suite of computational tests are performed to assess the proposed formulation, and its performance is analysed with respect to the impact of intelligent utilisation of the recharge points on reward acquisition. Finally, limitations of the proposed problem formulation are discussed, and avenues for future work are presented.
{"title":"The orienteering Problem with Replenishment","authors":"Nathan D. Wallace, He Kong, A. Hill, S. Sukkarieh","doi":"10.1109/CASE48305.2020.9216857","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216857","url":null,"abstract":"The planning of long-duration missions for resource-constrained agents is a longstanding challenge not only in field robotics research, but also in the fields of vehicle routing and logistics. To efficiently plan missions over a larger time scale than an agent’s resource capacity natively allows, it is necessary to exploit the availability of recharging stations, where an agent can replenish its spent resources at the cost of time. This paper presents the Orienteering Problem with Replenishment, a novel extension of the orienteering problem, which can fully utilise the existence of recharging stations by not only revisiting such stations, but also intelligently managing the amount of time spent recharging at each stop. By leveraging the above mechanisms for overcoming the resource limitations of the platform, the proposed problem formulation allows for the planning of longer term missions. A suite of computational tests are performed to assess the proposed formulation, and its performance is analysed with respect to the impact of intelligent utilisation of the recharge points on reward acquisition. Finally, limitations of the proposed problem formulation are discussed, and avenues for future work are presented.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124083665","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}
Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9216826
Jean Chagas Vaz, P. Oh
This paper presents a study to evaluate the effects of sloshing phenomena while a humanoid robot climbs stairs while carrying water containers. Currently humanoid robots can perform a wide range of tasks including handling tools, climbing ladders, and patrolling rough terrain. However, when it comes to manipulation of objects humanoids are fairly limited. This becomes more apparent when humanoids have to handle non-rigid objects. Although many full-sized humanoids cost an extensive amount of money, they fail to respond to common tasks during disaster relief such as delivering water to the victims or possible fires. After disasters such as Hurricane Maria, the need for humanoid robots to assist in these scenarios is becoming increasingly evident. In previous work the authors have developed an algorithm which allows the robot to walk while carrying water buckets. Experiments conducted use the full-sized humanoid DRC-Hubo as an experimental platform. Moreover, a sloshing reduction controller is implemented in order to suppress rocking disturbances. The system was integrated via ROS (Robot Operating System). Additionally, the sloshing reduction was evaluated based on sensor data evaluation.
{"title":"Model-Based Suppression Control for Liquid Vessels Carried by a Humanoid Robot While Stair-Climbing","authors":"Jean Chagas Vaz, P. Oh","doi":"10.1109/CASE48305.2020.9216826","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216826","url":null,"abstract":"This paper presents a study to evaluate the effects of sloshing phenomena while a humanoid robot climbs stairs while carrying water containers. Currently humanoid robots can perform a wide range of tasks including handling tools, climbing ladders, and patrolling rough terrain. However, when it comes to manipulation of objects humanoids are fairly limited. This becomes more apparent when humanoids have to handle non-rigid objects. Although many full-sized humanoids cost an extensive amount of money, they fail to respond to common tasks during disaster relief such as delivering water to the victims or possible fires. After disasters such as Hurricane Maria, the need for humanoid robots to assist in these scenarios is becoming increasingly evident. In previous work the authors have developed an algorithm which allows the robot to walk while carrying water buckets. Experiments conducted use the full-sized humanoid DRC-Hubo as an experimental platform. Moreover, a sloshing reduction controller is implemented in order to suppress rocking disturbances. The system was integrated via ROS (Robot Operating System). Additionally, the sloshing reduction was evaluated based on sensor data evaluation.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126243833","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}
Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9216843
Emma M. Flores, Xun Xu, Yuqian Lu
Cyber-Physical Systems (CPS) are an integral element of Industry 4.0, and these systems are said to have become gradually more intelligent throughout the years. Moreover, as technologies such as Artificial Intelligence and Internet of Things evolve, the suspicion arises on whether machines and humans could cohesively share control in the system. Despite efforts in the literature regarding the architecture and the implementation of CPS and Human CyberPhysical Systems (HCPS), more work needs to be done to highlight the similarities and strengths between people and machines. In this work, we take on the challenge to show that comparison from a human-skill perspective. This analysis highlights some of the human capabilities that have been moved to technologies. It also presents an updated list of human-machine capability differences. Besides, it identifies the human elements involved in HCPS as well as the skills included and required while working with HCPS.
{"title":"Human Cyber-Physical Systems: A skill-based correlation between humans and machines","authors":"Emma M. Flores, Xun Xu, Yuqian Lu","doi":"10.1109/CASE48305.2020.9216843","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216843","url":null,"abstract":"Cyber-Physical Systems (CPS) are an integral element of Industry 4.0, and these systems are said to have become gradually more intelligent throughout the years. Moreover, as technologies such as Artificial Intelligence and Internet of Things evolve, the suspicion arises on whether machines and humans could cohesively share control in the system. Despite efforts in the literature regarding the architecture and the implementation of CPS and Human CyberPhysical Systems (HCPS), more work needs to be done to highlight the similarities and strengths between people and machines. In this work, we take on the challenge to show that comparison from a human-skill perspective. This analysis highlights some of the human capabilities that have been moved to technologies. It also presents an updated list of human-machine capability differences. Besides, it identifies the human elements involved in HCPS as well as the skills included and required while working with HCPS.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126394745","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}
Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9216996
Heoncheol Lee
This paper addresses the problem of cooperative mapping in multi-robot SLAM (simultaneous localization and mapping) with unknown initial relative poses among robots. If mutual observation measurements between robots are available when the robots encounter each other, the map transformation between robots for cooperative mapping can be easily obtained. However, the mutual observation measurements require too strict assumptions such as a rendezvous and encounters, which is not practical in real multi-robot systems. Moreover, the mutual observation measurements may contain inevitable errors due to the errors in sensors. To relax the assumption and correct the errors, this paper proposes a one-way observation-based technique for cooperative mapping. The proposed technique was tested with datasets obtained by real experiments with two mobile robots. Each robot was equipped with a sensor fusion system to observe other robots. The test results showed that the proposed technique worked well and improved the accuracy of the cooperatively produced map.
研究了在初始相对姿态未知的情况下，多机器人SLAM (simultaneous localization and mapping)中的协同映射问题。如果机器人之间有相互观测的测量结果，那么机器人之间的地图转换就可以很容易地进行协作测绘。然而，相互观察测量需要过于严格的假设，如交会和相遇，这在实际的多机器人系统中是不现实的。此外，由于传感器的误差，相互观测的测量结果可能存在不可避免的误差。为了放宽假设并修正误差，本文提出了一种基于单向观测的协同映射技术。用两台移动机器人的真实实验数据集对该方法进行了验证。每个机器人都配备了传感器融合系统，以观察其他机器人。实验结果表明，该方法效果良好，提高了协同制作地图的精度。
{"title":"One-Way Observation-based Cooperative Robot Mapping","authors":"Heoncheol Lee","doi":"10.1109/CASE48305.2020.9216996","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216996","url":null,"abstract":"This paper addresses the problem of cooperative mapping in multi-robot SLAM (simultaneous localization and mapping) with unknown initial relative poses among robots. If mutual observation measurements between robots are available when the robots encounter each other, the map transformation between robots for cooperative mapping can be easily obtained. However, the mutual observation measurements require too strict assumptions such as a rendezvous and encounters, which is not practical in real multi-robot systems. Moreover, the mutual observation measurements may contain inevitable errors due to the errors in sensors. To relax the assumption and correct the errors, this paper proposes a one-way observation-based technique for cooperative mapping. The proposed technique was tested with datasets obtained by real experiments with two mobile robots. Each robot was equipped with a sensor fusion system to observe other robots. The test results showed that the proposed technique worked well and improved the accuracy of the cooperatively produced map.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125706512","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}
Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9217013
Nianzi Yang, Daqiang Guo, G. Huang
Assembly islands with fixed-position layout refers to a configuration in which the product remains at a fixed site and requires workers moving among different islands. This kind of production pattern is widely applied in heavy industrial manufacturing. However, due to the complexity and highly dynamic level of material and manpower flows, it is difficult to manage the production process in fixed-position assembly island. Graduation intelligent Manufacturing System (GiMS) is viewed as a promising system for tackling production with high complexity and uncertainty. To explore the application of GiMS in fixed product (minibus) assembly. This paper presents a demonstrative case study of minibus assembly under GiMS. IoT technologies are adopted to create smart manufacturing environment, and cloud-based services are developed for facilitating decision-making and daily operation. In addition, the implementation of three kinds of smart tickets in the case gives an explicit illustration of how it works.
{"title":"A Demonstrative Case Study of Minibus Assembly under GiMS","authors":"Nianzi Yang, Daqiang Guo, G. Huang","doi":"10.1109/CASE48305.2020.9217013","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9217013","url":null,"abstract":"Assembly islands with fixed-position layout refers to a configuration in which the product remains at a fixed site and requires workers moving among different islands. This kind of production pattern is widely applied in heavy industrial manufacturing. However, due to the complexity and highly dynamic level of material and manpower flows, it is difficult to manage the production process in fixed-position assembly island. Graduation intelligent Manufacturing System (GiMS) is viewed as a promising system for tackling production with high complexity and uncertainty. To explore the application of GiMS in fixed product (minibus) assembly. This paper presents a demonstrative case study of minibus assembly under GiMS. IoT technologies are adopted to create smart manufacturing environment, and cloud-based services are developed for facilitating decision-making and daily operation. In addition, the implementation of three kinds of smart tickets in the case gives an explicit illustration of how it works.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134209924","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}
Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9216812
Lanfang Zi, Benhe Gao
With the increasing volume of parcel sorting in the warehouse, it is more and more important to improve the throughput of the warehouse. In this paper, for the parcel sorting system based on AGVs, the throughput of the system is estimated by building an M/M/s queueing model. Considering the distribution of parcel destinations, we divide the warehouse into a popular area and an unpopular area. The popular area is consists of workstations and containers with a circular layout, while the unpopular area is distributed far away from the workstations with grid layout. The throughput of the system is estimated by estimating the completion time of sorting a parcel by an AGV. In order to find out the number of AGV in two areas, we design a heuristic search algorithm. Through the numerical experiments, we analyze the influence of the circular sorting probability, the number of AGVs, the number of workstations, and the layout of containers on the system throughput. This study can provide some valuable insights for practical work.
{"title":"Performance Estimating in an Innovative AGVs-based Parcel Sorting System Considering the Distribution of Destinations","authors":"Lanfang Zi, Benhe Gao","doi":"10.1109/CASE48305.2020.9216812","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216812","url":null,"abstract":"With the increasing volume of parcel sorting in the warehouse, it is more and more important to improve the throughput of the warehouse. In this paper, for the parcel sorting system based on AGVs, the throughput of the system is estimated by building an M/M/s queueing model. Considering the distribution of parcel destinations, we divide the warehouse into a popular area and an unpopular area. The popular area is consists of workstations and containers with a circular layout, while the unpopular area is distributed far away from the workstations with grid layout. The throughput of the system is estimated by estimating the completion time of sorting a parcel by an AGV. In order to find out the number of AGV in two areas, we design a heuristic search algorithm. Through the numerical experiments, we analyze the influence of the circular sorting probability, the number of AGVs, the number of workstations, and the layout of containers on the system throughput. This study can provide some valuable insights for practical work.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132096802","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}
Pub Date : 2020-08-01DOI: 10.1109/CASE48305.2020.9216970
Kyra Wang, Sihan Yang, Deepesh Kumar, N. Thakor
A key challenge in object manipulation using prosthetic hands is grasp detection and pose estimation, especially in cluttered scenes. Vision-based robotic grasping solutions typically only use conventional frame-based video cameras with high spatiotemporal redundancy, which is unsuitable for mobile platforms like prostheses with low processing power. On the other hand, while event-based dynamic vision sensors (DVS) have low spatiotemporal redundancy, their low resolution results in poor object segmentation and detection performance. In this paper we outline a novel hybrid solution inspired by the two-streams hypothesis of the neural processing of vision, utilizing both a frame-based video camera and a DVS to counter the pitfalls of both systems. By using computationally efficient object detection methods on the frame-based camera to highlight regions-of-interest (ROIs) for the DVS, we are able to perform pose estimation by computing the smallest axis of DVS events generated in the ROI. The proposed approach allows us to rapidly determine the required wrist rotation and a suitable grasp type to pick up objects using a prosthetic hand. Results on a laptop show that our method matches the accuracy of a conventional solution that employs only a frame-based video camera, while achieving 77.29% faster inference speed.
{"title":"Hybrid Frame-Event Solution for Vision-Based Grasp and Pose Detection of Objects","authors":"Kyra Wang, Sihan Yang, Deepesh Kumar, N. Thakor","doi":"10.1109/CASE48305.2020.9216970","DOIUrl":"https://doi.org/10.1109/CASE48305.2020.9216970","url":null,"abstract":"A key challenge in object manipulation using prosthetic hands is grasp detection and pose estimation, especially in cluttered scenes. Vision-based robotic grasping solutions typically only use conventional frame-based video cameras with high spatiotemporal redundancy, which is unsuitable for mobile platforms like prostheses with low processing power. On the other hand, while event-based dynamic vision sensors (DVS) have low spatiotemporal redundancy, their low resolution results in poor object segmentation and detection performance. In this paper we outline a novel hybrid solution inspired by the two-streams hypothesis of the neural processing of vision, utilizing both a frame-based video camera and a DVS to counter the pitfalls of both systems. By using computationally efficient object detection methods on the frame-based camera to highlight regions-of-interest (ROIs) for the DVS, we are able to perform pose estimation by computing the smallest axis of DVS events generated in the ROI. The proposed approach allows us to rapidly determine the required wrist rotation and a suitable grasp type to pick up objects using a prosthetic hand. Results on a laptop show that our method matches the accuracy of a conventional solution that employs only a frame-based video camera, while achieving 77.29% faster inference speed.","PeriodicalId":212181,"journal":{"name":"2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132405154","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：