Pub Date : 2016-04-01DOI: 10.1109/ICCPS.2016.7479105
I. Saha, Rattanachai Ramaithitima, Vijay R. Kumar, George J. Pappas, S. Seshia
We consider the collision-free motion planning problem for a group of robots using a library of motion primitives. To cope with the complexity of the problem, we introduce an incremental algorithm based on an SMT solver, where we divide the robots into small groups based on a priority assignment algorithm. The priority assignment algorithm assigns priorities to the robots in such a way that the robots do not block the cost-optimal trajectories of the other robots. While the priority assignment algorithm attempts to assign distinct priorities to the robots, the algorithm ends up with assigning the same priority to some robots due to the dependencies among themselves. The algorithm includes the robots with the same priority in the same group. Our incremental algorithm then considers the robot groups one by one based on their priority and synthesizes the trajectories for the group of robots together. While synthesizing the trajectories for the robots in one group, the algorithm considers the higher priority robots as dynamic obstacles, and introduces a minimal delay in executing the cost-optimal trajectories to avoid collision with the higher priority robots. We apply our method to synthesize trajectories for a group of quadrotors in our lab space. Experimental results show that we can synthesize trajectories for tens of robots with complex dynamics in a reasonable time.
{"title":"Implan: Scalable Incremental Motion Planning for Multi-Robot Systems","authors":"I. Saha, Rattanachai Ramaithitima, Vijay R. Kumar, George J. Pappas, S. Seshia","doi":"10.1109/ICCPS.2016.7479105","DOIUrl":"https://doi.org/10.1109/ICCPS.2016.7479105","url":null,"abstract":"We consider the collision-free motion planning problem for a group of robots using a library of motion primitives. To cope with the complexity of the problem, we introduce an incremental algorithm based on an SMT solver, where we divide the robots into small groups based on a priority assignment algorithm. The priority assignment algorithm assigns priorities to the robots in such a way that the robots do not block the cost-optimal trajectories of the other robots. While the priority assignment algorithm attempts to assign distinct priorities to the robots, the algorithm ends up with assigning the same priority to some robots due to the dependencies among themselves. The algorithm includes the robots with the same priority in the same group. Our incremental algorithm then considers the robot groups one by one based on their priority and synthesizes the trajectories for the group of robots together. While synthesizing the trajectories for the robots in one group, the algorithm considers the higher priority robots as dynamic obstacles, and introduces a minimal delay in executing the cost-optimal trajectories to avoid collision with the higher priority robots. We apply our method to synthesize trajectories for a group of quadrotors in our lab space. Experimental results show that we can synthesize trajectories for tens of robots with complex dynamics in a reasonable time.","PeriodicalId":6619,"journal":{"name":"2016 ACM/IEEE 7th International Conference on Cyber-Physical Systems (ICCPS)","volume":"62 1","pages":"1-10"},"PeriodicalIF":0.0,"publicationDate":"2016-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78749504","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 : 2016-04-01DOI: 10.1109/ICCPS.2016.7479096
Marten Lohstroh, Christopher X. Brooks, Edward A. Lee
We demonstrate CapeCode, a tool for composing actor-oriented building blocks for applications in the Internet of Things design space.
我们演示了CapeCode，这是一个为物联网设计空间中的应用程序组合面向参与者的构建块的工具。
{"title":"Demo Abstract: Building IoT Applications with Accessors in CapeCode","authors":"Marten Lohstroh, Christopher X. Brooks, Edward A. Lee","doi":"10.1109/ICCPS.2016.7479096","DOIUrl":"https://doi.org/10.1109/ICCPS.2016.7479096","url":null,"abstract":"We demonstrate CapeCode, a tool for composing actor-oriented building blocks for applications in the Internet of Things design space.","PeriodicalId":6619,"journal":{"name":"2016 ACM/IEEE 7th International Conference on Cyber-Physical Systems (ICCPS)","volume":"19 1","pages":"1-1"},"PeriodicalIF":0.0,"publicationDate":"2016-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72632916","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 : 2016-01-20DOI: 10.1109/ICCPS.2016.7479093
Madhur Behl, Achin Jain, R. Mangharam
Demand response (DR) is becoming important as the volatility on the grid continues to increase. Current DR approaches are either completely manual or involve deriving first principles based models which are extremely cost and time prohibitive to build. We consider the problem of data-driven DR for large buildings which involves predicting the demand response baseline, evaluating fixed DR strategies and synthesizing DR control actions. We provide a model based control with regression trees algorithm (mbCRT), which allows us to perform closed-loop control for DR strategy synthesis for large buildings. Our data-driven control synthesis algorithm outperforms rule- based DR by 17% for a large DoE commercial reference building and leads to a curtailment of 380 kW and over $45,000 in savings. Our methods have been integrated into an open source tool called DR-Advisor, which acts as a recommender system for the building's facilities manager and provides suitable control actions to meet the desired load curtailment while maintaining operations and maximizing the economic reward. DR-Advisor achieves 92.8% to 98.9% prediction accuracy for 8 buildings on Penn's campus. We compare DR-Advisor with other data driven methods and rank 2nd on ASHRAE's benchmarking data-set for energy prediction.
{"title":"Data-Driven Modeling, Control and Tools for Cyber-Physical Energy Systems","authors":"Madhur Behl, Achin Jain, R. Mangharam","doi":"10.1109/ICCPS.2016.7479093","DOIUrl":"https://doi.org/10.1109/ICCPS.2016.7479093","url":null,"abstract":"Demand response (DR) is becoming important as the volatility on the grid continues to increase. Current DR approaches are either completely manual or involve deriving first principles based models which are extremely cost and time prohibitive to build. We consider the problem of data-driven DR for large buildings which involves predicting the demand response baseline, evaluating fixed DR strategies and synthesizing DR control actions. We provide a model based control with regression trees algorithm (mbCRT), which allows us to perform closed-loop control for DR strategy synthesis for large buildings. Our data-driven control synthesis algorithm outperforms rule- based DR by 17% for a large DoE commercial reference building and leads to a curtailment of 380 kW and over $45,000 in savings. Our methods have been integrated into an open source tool called DR-Advisor, which acts as a recommender system for the building's facilities manager and provides suitable control actions to meet the desired load curtailment while maintaining operations and maximizing the economic reward. DR-Advisor achieves 92.8% to 98.9% prediction accuracy for 8 buildings on Penn's campus. We compare DR-Advisor with other data driven methods and rank 2nd on ASHRAE's benchmarking data-set for energy prediction.","PeriodicalId":6619,"journal":{"name":"2016 ACM/IEEE 7th International Conference on Cyber-Physical Systems (ICCPS)","volume":"12 1","pages":"1-10"},"PeriodicalIF":0.0,"publicationDate":"2016-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84982334","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 : 2015-12-24DOI: 10.1109/ICCPS.2016.7479069
Chao Liu, Sambuddha Ghosal, Zhanhong Jiang, S. Sarkar
Modern distributed cyber-physical systems (CPSs) encounter a large variety of physical faults and cyber anomalies and in many cases, they are vulnerable to catastrophic fault propagation scenarios due to strong connectivity among the sub-systems. This paper presents a new data-driven framework for system-wide anomaly detection for addressing such issues. The framework is based on a spatiotemporal feature extraction scheme built on the concept of symbolic dynamics for discovering and representing causal interactions among the subsystems of a CPS. The extracted spatiotemporal features are then used to learn system-wide patterns via a Restricted Boltzmann Machine (RBM). The results show that: (1) the RBM free energy in the off-nominal conditions is different from that in the nominal conditions and can be used for anomaly detection; (2) the framework can capture multiple nominal modes with one graphical model; (3) the case studies with simulated data and an integrated building system validate the proposed approach.
{"title":"An Unsupervised Spatiotemporal Graphical Modeling Approach to Anomaly Detection in Distributed CPS","authors":"Chao Liu, Sambuddha Ghosal, Zhanhong Jiang, S. Sarkar","doi":"10.1109/ICCPS.2016.7479069","DOIUrl":"https://doi.org/10.1109/ICCPS.2016.7479069","url":null,"abstract":"Modern distributed cyber-physical systems (CPSs) encounter a large variety of physical faults and cyber anomalies and in many cases, they are vulnerable to catastrophic fault propagation scenarios due to strong connectivity among the sub-systems. This paper presents a new data-driven framework for system-wide anomaly detection for addressing such issues. The framework is based on a spatiotemporal feature extraction scheme built on the concept of symbolic dynamics for discovering and representing causal interactions among the subsystems of a CPS. The extracted spatiotemporal features are then used to learn system-wide patterns via a Restricted Boltzmann Machine (RBM). The results show that: (1) the RBM free energy in the off-nominal conditions is different from that in the nominal conditions and can be used for anomaly detection; (2) the framework can capture multiple nominal modes with one graphical model; (3) the case studies with simulated data and an integrated building system validate the proposed approach.","PeriodicalId":6619,"journal":{"name":"2016 ACM/IEEE 7th International Conference on Cyber-Physical Systems (ICCPS)","volume":"39 1","pages":"1-10"},"PeriodicalIF":0.0,"publicationDate":"2015-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90685209","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 : 2015-12-23DOI: 10.1109/ICCPS.2016.7479095
Kin Gwn Lore, Nicholas Sweet, Kundan Kumar, N. Ahmed, S. Sarkar
Effective human-machine collaboration can significantly improve many learning and planning strategies for information gathering via fusion of 'hard' and 'soft' data originating from machine and human sensors, respectively. However, gathering the most informative data from human sensors without task overloading remains a critical technical challenge. In this context, Value of Information (VOI) is a crucial decision- theoretic metric for scheduling interaction with human sensors. We present a new Deep Learning based VOI estimation framework that can be used to schedule collaborative human-machine sensing with efficient online inference and minimal policy hand-tuning. Supervised learning is used to train deep convolutional neural networks (CNNs) to extract hierarchical features from 'images' of belief spaces obtained via data fusion. These features can be associated with soft data query choices to reliably compute VOI for human interaction. The CNN framework is described in detail, and a performance comparison to a feature- based POMDP scheduling policy is provided. The practical feasibility of our method is also demonstrated on a mobile robotic search problem with language-based semantic human sensor inputs.
{"title":"Deep Value of Information Estimators for Collaborative Human-Machine Information Gathering","authors":"Kin Gwn Lore, Nicholas Sweet, Kundan Kumar, N. Ahmed, S. Sarkar","doi":"10.1109/ICCPS.2016.7479095","DOIUrl":"https://doi.org/10.1109/ICCPS.2016.7479095","url":null,"abstract":"Effective human-machine collaboration can significantly improve many learning and planning strategies for information gathering via fusion of 'hard' and 'soft' data originating from machine and human sensors, respectively. However, gathering the most informative data from human sensors without task overloading remains a critical technical challenge. In this context, Value of Information (VOI) is a crucial decision- theoretic metric for scheduling interaction with human sensors. We present a new Deep Learning based VOI estimation framework that can be used to schedule collaborative human-machine sensing with efficient online inference and minimal policy hand-tuning. Supervised learning is used to train deep convolutional neural networks (CNNs) to extract hierarchical features from 'images' of belief spaces obtained via data fusion. These features can be associated with soft data query choices to reliably compute VOI for human interaction. The CNN framework is described in detail, and a performance comparison to a feature- based POMDP scheduling policy is provided. The practical feasibility of our method is also demonstrated on a mobile robotic search problem with language-based semantic human sensor inputs.","PeriodicalId":6619,"journal":{"name":"2016 ACM/IEEE 7th International Conference on Cyber-Physical Systems (ICCPS)","volume":"13 1","pages":"1-10"},"PeriodicalIF":0.0,"publicationDate":"2015-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85035119","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}
Maxim Buevich, Xiao Zhang, Oliver Shih, Dan Schnitzer, Tristan Escalada, Arthur Jacquiau-Chamski, Jon Thacker, Anthony G. Rowe
Non-Technical Loss (NTL) represents a major challenge when providing reliable electrical service in developing countries, where it often accounts for 11-15% of total generation capacity [1]. NTL is caused by a variety of factors such as theft, unmetered homes, and inability to pay, which at volume can lead to system instability, grid failure, and major financial losses for providers. In this paper, we investigate error sources and techniques for separating NTL from total losses in microgrids. We adopt and compare two classes of approaches for detecting NTL: (1) model- driven and (2) data- driven. The model-driven class considers the primary sources of state uncertainty including line losses, meter consumption, meter calibration error, packet loss, and sample synchronization error. In the data-driven class, we use two approaches that learn grid state based on training data. The first approach uses a regression technique on an NTL-free period of grid operation to capture the relationship between state error and total consumption. The second approach uses an SVM trained on synthetic NTL data. Both classes of approaches can provide a confidence interval based on the amount of detected NTL. We experimentally evaluate and compare the approaches on wireless meter data collected from a 525-home microgrid deployed in Les Anglais, Haiti. We see that both are quite effective, but that the data-driven class is significantly easier to implement. In both cases, we are able to experimentally evaluate to what degree we can reliably separate NTL from total losses.
{"title":"Microgrid Losses: When the Whole Is Greater Than the Sum of Its Parts","authors":"Maxim Buevich, Xiao Zhang, Oliver Shih, Dan Schnitzer, Tristan Escalada, Arthur Jacquiau-Chamski, Jon Thacker, Anthony G. Rowe","doi":"10.1145/2821650.2821676","DOIUrl":"https://doi.org/10.1145/2821650.2821676","url":null,"abstract":"Non-Technical Loss (NTL) represents a major challenge when providing reliable electrical service in developing countries, where it often accounts for 11-15% of total generation capacity [1]. NTL is caused by a variety of factors such as theft, unmetered homes, and inability to pay, which at volume can lead to system instability, grid failure, and major financial losses for providers. In this paper, we investigate error sources and techniques for separating NTL from total losses in microgrids. We adopt and compare two classes of approaches for detecting NTL: (1) model- driven and (2) data- driven. The model-driven class considers the primary sources of state uncertainty including line losses, meter consumption, meter calibration error, packet loss, and sample synchronization error. In the data-driven class, we use two approaches that learn grid state based on training data. The first approach uses a regression technique on an NTL-free period of grid operation to capture the relationship between state error and total consumption. The second approach uses an SVM trained on synthetic NTL data. Both classes of approaches can provide a confidence interval based on the amount of detected NTL. We experimentally evaluate and compare the approaches on wireless meter data collected from a 525-home microgrid deployed in Les Anglais, Haiti. We see that both are quite effective, but that the data-driven class is significantly easier to implement. In both cases, we are able to experimentally evaluate to what degree we can reliably separate NTL from total losses.","PeriodicalId":6619,"journal":{"name":"2016 ACM/IEEE 7th International Conference on Cyber-Physical Systems (ICCPS)","volume":"30 1","pages":"1-10"},"PeriodicalIF":0.0,"publicationDate":"2015-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76817740","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}
Cloud service providers such as Microsoft and Google are beginning to power up their datacenters using multiple energy sources. To reduce cost and emission, they incorporate green energy sources into the power supply, while to improve service availability, they back up datacenters using traditional (usually brown) energy sources. However, challenge arises due to distinct characteristics of energy sources used for different goals. How to select optimal energy sources and plan their capacity for constructing datacenters to meet cost, emission and service availability requirement remains to be fully explored. This work provides a holistic solution to address this problem. We present GreenPlanning, a framework to strike a judicious balance among multiple energy sources, grid power and energy storage devices for a datacenter in terms of the above three goals. GreenPlanning investigates different features and operations of a wide spectrum of green and brown energy sources available to datacenters. The framework minimizes the lifetime total cost including both capital and operational cost for a datacenter. We conduct extensive simulations to evaluate GreenPlanning with real-life computational workload and meteorological data traces. Results demonstrate that GreenPlanning can reduce the lifetime total cost and emission by more than 50% compared to traditional configurations, while still satisfying service availability requirement.
{"title":"GreenPlanning: Optimal Energy Source Selection and Capacity Planning for Green Datacenters","authors":"Fanxin Kong, Xue Liu","doi":"10.1145/2591971.2592025","DOIUrl":"https://doi.org/10.1145/2591971.2592025","url":null,"abstract":"Cloud service providers such as Microsoft and Google are beginning to power up their datacenters using multiple energy sources. To reduce cost and emission, they incorporate green energy sources into the power supply, while to improve service availability, they back up datacenters using traditional (usually brown) energy sources. However, challenge arises due to distinct characteristics of energy sources used for different goals. How to select optimal energy sources and plan their capacity for constructing datacenters to meet cost, emission and service availability requirement remains to be fully explored. This work provides a holistic solution to address this problem. We present GreenPlanning, a framework to strike a judicious balance among multiple energy sources, grid power and energy storage devices for a datacenter in terms of the above three goals. GreenPlanning investigates different features and operations of a wide spectrum of green and brown energy sources available to datacenters. The framework minimizes the lifetime total cost including both capital and operational cost for a datacenter. We conduct extensive simulations to evaluate GreenPlanning with real-life computational workload and meteorological data traces. Results demonstrate that GreenPlanning can reduce the lifetime total cost and emission by more than 50% compared to traditional configurations, while still satisfying service availability requirement.","PeriodicalId":6619,"journal":{"name":"2016 ACM/IEEE 7th International Conference on Cyber-Physical Systems (ICCPS)","volume":"12 1","pages":"1-10"},"PeriodicalIF":0.0,"publicationDate":"2014-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76384969","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 : 2014-04-15DOI: 10.1109/ICCPS.2014.6843731
I. Yu, Iijima Koichiro, Fukumoto Takashi, Yoshioka Masahiro
We propose a power supply-demand scheduling method aimed at realization of our new conceptual model, “Symbiosis-autonomous decentralized system”, that realizes an optimal resource allocation by cooperation and accommodation between stakeholders. Important properties of the cooperative FEMS are power planning in cooperation with production plan and another stakeholder's uncertainty. Our scheduling method resolve the above-mentioned subjects by decreasing of an administrator's workloads for power demand adjustment (PCR strategy), and decreasing power shortage risk for an emergent supply-demand change by external factors (RCR strategy).
{"title":"WiP Abstract: Supply-demand Planning Method in cooperation with factory production schedule aimed at the realization of Symbiosis-Autonomous Decentralized System","authors":"I. Yu, Iijima Koichiro, Fukumoto Takashi, Yoshioka Masahiro","doi":"10.1109/ICCPS.2014.6843731","DOIUrl":"https://doi.org/10.1109/ICCPS.2014.6843731","url":null,"abstract":"We propose a power supply-demand scheduling method aimed at realization of our new conceptual model, “Symbiosis-autonomous decentralized system”, that realizes an optimal resource allocation by cooperation and accommodation between stakeholders. Important properties of the cooperative FEMS are power planning in cooperation with production plan and another stakeholder's uncertainty. Our scheduling method resolve the above-mentioned subjects by decreasing of an administrator's workloads for power demand adjustment (PCR strategy), and decreasing power shortage risk for an emergent supply-demand change by external factors (RCR strategy).","PeriodicalId":6619,"journal":{"name":"2016 ACM/IEEE 7th International Conference on Cyber-Physical Systems (ICCPS)","volume":"1 1","pages":"218-218"},"PeriodicalIF":0.0,"publicationDate":"2014-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87612984","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}
Efficient design is required for a cyber-physical system, as we need to trade off the complexity and performance benefits. We consider the CPS of a traffic-light controller at an isolated intersection that is used by autonomous, semi-autonomous, and human-driven automobiles. Existing traffic systems are vulnerable to accidents (more than 1 million people die in automotive accidents globally) and undesired traffic delays (the average U.S. driver spends a week stuck in traffic every year). The next generation of traffic-light control systems should protect against these disruptions while maintaining enhanced control of the system to optimize features of interest. The potential benefits of such a system include increased safety in the presence of higher density traffic, increased fuel and time efficiency (as less time is wasted in queuing), and decreased demands on drivers to make driving decisions. Here, we demonstrate a novel approach to adjusting the cycle length, yellow time, and red-to-green ratios of a traffic signal by minimizing the average loss per vehicle due the presence of the signal.
{"title":"Real-time adaptive signaling for isolated intersections","authors":"Sai Prathyusha Peddi","doi":"10.1145/2502524.2502575","DOIUrl":"https://doi.org/10.1145/2502524.2502575","url":null,"abstract":"Efficient design is required for a cyber-physical system, as we need to trade off the complexity and performance benefits. We consider the CPS of a traffic-light controller at an isolated intersection that is used by autonomous, semi-autonomous, and human-driven automobiles. Existing traffic systems are vulnerable to accidents (more than 1 million people die in automotive accidents globally) and undesired traffic delays (the average U.S. driver spends a week stuck in traffic every year). The next generation of traffic-light control systems should protect against these disruptions while maintaining enhanced control of the system to optimize features of interest. The potential benefits of such a system include increased safety in the presence of higher density traffic, increased fuel and time efficiency (as less time is wasted in queuing), and decreased demands on drivers to make driving decisions. Here, we demonstrate a novel approach to adjusting the cycle length, yellow time, and red-to-green ratios of a traffic signal by minimizing the average loss per vehicle due the presence of the signal.","PeriodicalId":6619,"journal":{"name":"2016 ACM/IEEE 7th International Conference on Cyber-Physical Systems (ICCPS)","volume":"6 1","pages":"256"},"PeriodicalIF":0.0,"publicationDate":"2013-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75121708","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}
Song Han, A. Mok, Jianyong Meng, Yi-Hung Wei, Pei-Chi Huang, Xiuming Zhu, L. Sentis, Kwan-Suk Kim, R. Miikkulainen, J. Menashe
This paper introduces the concept of a cyberphysical avatar which is defined to be a semi-autonomous robotic system that adjusts to an unstructured environment and performs physical tasks subject to critical timing constraints while under human supervision. Cyberphysical avatar integrates the recent advance in three technologies: body-compliant control in robotics, neuroevolution in machine learning and QoS guarantees in real-time communication. Body-compliant control is essential for operator safety since cyberphysical avatars perform cooperative tasks in close proximity to humans. Neuroevolution technique is essential for "programming" cyberphysical avatars inasmuch as they are to be used by non-experts for a large array of tasks, some unforeseen, in an unstructured environment. QoS-guaranteed real-time communication is essential to provide predictable, bounded-time response in human-avatar interaction. By integrating these technologies, we have built a prototype cyberphysical avatar testbed.
{"title":"Architecture of a cyberphysical avatar","authors":"Song Han, A. Mok, Jianyong Meng, Yi-Hung Wei, Pei-Chi Huang, Xiuming Zhu, L. Sentis, Kwan-Suk Kim, R. Miikkulainen, J. Menashe","doi":"10.1145/2502524.2502550","DOIUrl":"https://doi.org/10.1145/2502524.2502550","url":null,"abstract":"This paper introduces the concept of a cyberphysical avatar which is defined to be a semi-autonomous robotic system that adjusts to an unstructured environment and performs physical tasks subject to critical timing constraints while under human supervision. Cyberphysical avatar integrates the recent advance in three technologies: body-compliant control in robotics, neuroevolution in machine learning and QoS guarantees in real-time communication. Body-compliant control is essential for operator safety since cyberphysical avatars perform cooperative tasks in close proximity to humans. Neuroevolution technique is essential for \"programming\" cyberphysical avatars inasmuch as they are to be used by non-experts for a large array of tasks, some unforeseen, in an unstructured environment. QoS-guaranteed real-time communication is essential to provide predictable, bounded-time response in human-avatar interaction. By integrating these technologies, we have built a prototype cyberphysical avatar testbed.","PeriodicalId":6619,"journal":{"name":"2016 ACM/IEEE 7th International Conference on Cyber-Physical Systems (ICCPS)","volume":"223 1","pages":"189-198"},"PeriodicalIF":0.0,"publicationDate":"2013-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76703342","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：