HereBoy is an evolutionary algorithm that combines features from genetic algorithms and simulated annealing, and also adds a new methodology for exploring the search space. It is particularly well suited for exploring large spaces, like those associated with evolvable hardware, although it can be applied to a wide range of search/optimization problems. Experimental data consistently shows that when compared to both genetic algorithms and simulated annealing, HereBoy requires up to 100X fewer iterations than a genetic algorithm and up to 10X fewer iterations than simulated annealing. In some cases HereBoy is able to solve problems to a degree of accuracy that a generic algorithm is unable to achieve. HereBoy also scales from small problems to larger problems significantly better than the other two algorithms.
{"title":"HereBoy: a fast evolutionary algorithm","authors":"Delon Levi","doi":"10.1109/EH.2000.869338","DOIUrl":"https://doi.org/10.1109/EH.2000.869338","url":null,"abstract":"HereBoy is an evolutionary algorithm that combines features from genetic algorithms and simulated annealing, and also adds a new methodology for exploring the search space. It is particularly well suited for exploring large spaces, like those associated with evolvable hardware, although it can be applied to a wide range of search/optimization problems. Experimental data consistently shows that when compared to both genetic algorithms and simulated annealing, HereBoy requires up to 100X fewer iterations than a genetic algorithm and up to 10X fewer iterations than simulated annealing. In some cases HereBoy is able to solve problems to a degree of accuracy that a generic algorithm is unable to achieve. HereBoy also scales from small problems to larger problems significantly better than the other two algorithms.","PeriodicalId":432338,"journal":{"name":"Proceedings. The Second NASA/DoD Workshop on Evolvable Hardware","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129915155","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}
A. Stoica, D. Keymeulen, R. Zebulum, A. Thakoor, T. Daud, Gerhard Klimeck, Y. Jin, R. Tawel, V. Duong
Evolvable Hardware (EHW) refers to HW design and self reconfiguration using evolutionary/genetic mechanisms. The paper presents an overview of some key concepts of EHW, describing also a set of selected applications. A fine-grained Field Programmable Transistor Array (FPTA) architecture for reconfigurable hardware is presented as an example of an initial effort toward evolution-oriented devices. Evolutionary experiments in simulations and with a FPTA chip in-the-loop demonstrate automatic synthesis of electronic circuits. Unconventional circuits, for which there are no textbook design guidelines, are particularly appealing to evolvable hardware. To illustrate this situation, one demonstrates here the evolution of circuits implementing parametrical connectives for fuzzy logics. In addition to synthesizing circuits for new functions, evolvable hardware can be used to preserve existing functions and achieve fault-tolerance, determining circuit configurations that circumvent the faults. In addition, we illustrate with an example how evolution can recover functionality lost due to an increase in temperature. In the particular case of space applications, these characteristics are extremely important for enabling spacecraft to survive harsh environments and to have long life.
{"title":"Evolution of analog circuits on field programmable transistor arrays","authors":"A. Stoica, D. Keymeulen, R. Zebulum, A. Thakoor, T. Daud, Gerhard Klimeck, Y. Jin, R. Tawel, V. Duong","doi":"10.1109/EH.2000.869347","DOIUrl":"https://doi.org/10.1109/EH.2000.869347","url":null,"abstract":"Evolvable Hardware (EHW) refers to HW design and self reconfiguration using evolutionary/genetic mechanisms. The paper presents an overview of some key concepts of EHW, describing also a set of selected applications. A fine-grained Field Programmable Transistor Array (FPTA) architecture for reconfigurable hardware is presented as an example of an initial effort toward evolution-oriented devices. Evolutionary experiments in simulations and with a FPTA chip in-the-loop demonstrate automatic synthesis of electronic circuits. Unconventional circuits, for which there are no textbook design guidelines, are particularly appealing to evolvable hardware. To illustrate this situation, one demonstrates here the evolution of circuits implementing parametrical connectives for fuzzy logics. In addition to synthesizing circuits for new functions, evolvable hardware can be used to preserve existing functions and achieve fault-tolerance, determining circuit configurations that circumvent the faults. In addition, we illustrate with an example how evolution can recover functionality lost due to an increase in temperature. In the particular case of space applications, these characteristics are extremely important for enabling spacecraft to survive harsh environments and to have long life.","PeriodicalId":432338,"journal":{"name":"Proceedings. The Second NASA/DoD Workshop on Evolvable Hardware","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130246139","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}
Evolvable Hardware (EHW) has the potential to become a new target hardware for complex real-world applications. However, there are several problems that would have to be solved to make it widely applicable. This includes the difficulties in evolving large systems and the lack of generalization of gate level EHW. This paper proposes new methods targeting these problems, where a system is evolved by evolving smaller sub-systems. The experiments are based on a simplified image recognition task to be used in a roadway departure prevention system and later in an autonomous driving system. Special concern has been given to improve the generalization of the system. Experiments show that the number of generations required for evolution by the new method can be substantially reduced compared to evolving a system directly. This is with no reduction of the performance in the final system. Improvement in the generalization is shown as well.
{"title":"Scalable evolvable hardware applied to road image recognition","authors":"J. Tørresen","doi":"10.1109/EH.2000.869362","DOIUrl":"https://doi.org/10.1109/EH.2000.869362","url":null,"abstract":"Evolvable Hardware (EHW) has the potential to become a new target hardware for complex real-world applications. However, there are several problems that would have to be solved to make it widely applicable. This includes the difficulties in evolving large systems and the lack of generalization of gate level EHW. This paper proposes new methods targeting these problems, where a system is evolved by evolving smaller sub-systems. The experiments are based on a simplified image recognition task to be used in a roadway departure prevention system and later in an autonomous driving system. Special concern has been given to improve the generalization of the system. Experiments show that the number of generations required for evolution by the new method can be substantially reduced compared to evolving a system directly. This is with no reduction of the performance in the final system. Improvement in the generalization is shown as well.","PeriodicalId":432338,"journal":{"name":"Proceedings. The Second NASA/DoD Workshop on Evolvable Hardware","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121882195","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}
The GOLEM project is an attempt to extend evolutionary techniques into the physical world by evolving diverse electro-mechanical machines (robots) that can be fabricated automatically. In this work we go beyond evolution of hardware controllers and demonstrate for the first time a path that allows transfer of virtual diversity of morphology into reality. Our approach is based on the use of only elementary building blocks in both the design and embodiment. We describe a set of preliminary experiments evolving electromechanical systems composed of thermoplastic, linear actuators and neurons for the task of locomotion, first in simulation then in reality. Using 3D solid printing, these creatures then replicate automatically into reality where they faithfully reproduce the performance of their virtual ancestors.
{"title":"The GOLEM project: evolving hardware bodies and brains","authors":"J. Pollack, Hod Lipson","doi":"10.1109/EH.2000.869340","DOIUrl":"https://doi.org/10.1109/EH.2000.869340","url":null,"abstract":"The GOLEM project is an attempt to extend evolutionary techniques into the physical world by evolving diverse electro-mechanical machines (robots) that can be fabricated automatically. In this work we go beyond evolution of hardware controllers and demonstrate for the first time a path that allows transfer of virtual diversity of morphology into reality. Our approach is based on the use of only elementary building blocks in both the design and embodiment. We describe a set of preliminary experiments evolving electromechanical systems composed of thermoplastic, linear actuators and neurons for the task of locomotion, first in simulation then in reality. Using 3D solid printing, these creatures then replicate automatically into reality where they faithfully reproduce the performance of their virtual ancestors.","PeriodicalId":432338,"journal":{"name":"Proceedings. The Second NASA/DoD Workshop on Evolvable Hardware","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125560505","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}
Ho-Sik Seok, Kwang-Ju Lee, Byoung-Tak Zhang, Dong-Wook Lee, K. Sim
Evolvable hardware is able to offer considerably higher performance than general-purpose processors and significantly more flexibility than ASICs. In order to take the advantages of general-purpose processors and ASICs, dividing a complex process into subprocesses is essential. In this paper, we propose a evolutionary method called context switching that splits a task into a set of subtasks whose complexity is manageable on the given hardware. The method is based on genetic programming. Due to its expressive power generic program can represent flexible strategies for decomposing complex tasks. The effectiveness of context switching is demonstrated on the design of adaptive controllers for a team of autonomous mobile robots.
{"title":"Genetic programming of process decomposition strategies for evolvable hardware","authors":"Ho-Sik Seok, Kwang-Ju Lee, Byoung-Tak Zhang, Dong-Wook Lee, K. Sim","doi":"10.1109/EH.2000.869339","DOIUrl":"https://doi.org/10.1109/EH.2000.869339","url":null,"abstract":"Evolvable hardware is able to offer considerably higher performance than general-purpose processors and significantly more flexibility than ASICs. In order to take the advantages of general-purpose processors and ASICs, dividing a complex process into subprocesses is essential. In this paper, we propose a evolutionary method called context switching that splits a task into a set of subtasks whose complexity is manageable on the given hardware. The method is based on genetic programming. Due to its expressive power generic program can represent flexible strategies for decomposing complex tasks. The effectiveness of context switching is demonstrated on the design of adaptive controllers for a team of autonomous mobile robots.","PeriodicalId":432338,"journal":{"name":"Proceedings. The Second NASA/DoD Workshop on Evolvable Hardware","volume":"1954 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129523409","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}
One important feature of signal processing is coping with noise. In a non-adaptive filter, characteristics of the filter may be refined to remove noise. One method of achieving this is to use evolution to decide the filter characteristics. However, if the noise level is sufficient or the input signal is not of the required type for the output signal required, then a satisfactory output signal may not be achievable. To be able to achieve the required output signal for a wide range of input signals and noise, it is desirable to be able to adjust both the characteristics and the type of the filter. In this way the resulting filter may be said to be an adaptive filter. In this paper we propose an on-chip solution for an adaptive digital filter using an on-chip evolvable hardware method. We highlight a challenge within evolvable hardware for adaptive designs and that is to find efficient ways in which sufficient genetic material will be available to the evolution process. This problem appears when the evolution process is automatically restarted so as to adapt to a change in the environment.
{"title":"Evolving an adaptive digital filter","authors":"G. Tufte, P. Haddow","doi":"10.1109/EH.2000.869352","DOIUrl":"https://doi.org/10.1109/EH.2000.869352","url":null,"abstract":"One important feature of signal processing is coping with noise. In a non-adaptive filter, characteristics of the filter may be refined to remove noise. One method of achieving this is to use evolution to decide the filter characteristics. However, if the noise level is sufficient or the input signal is not of the required type for the output signal required, then a satisfactory output signal may not be achievable. To be able to achieve the required output signal for a wide range of input signals and noise, it is desirable to be able to adjust both the characteristics and the type of the filter. In this way the resulting filter may be said to be an adaptive filter. In this paper we propose an on-chip solution for an adaptive digital filter using an on-chip evolvable hardware method. We highlight a challenge within evolvable hardware for adaptive designs and that is to find efficient ways in which sufficient genetic material will be available to the evolution process. This problem appears when the evolution process is automatically restarted so as to adapt to a change in the environment.","PeriodicalId":432338,"journal":{"name":"Proceedings. The Second NASA/DoD Workshop on Evolvable Hardware","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129055989","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}
Evolvable Hardware (EHW) has been proposed as a new technique to design complex systems. Often, complex systems turn out to be very difficult to evolve. The problem is that a general strategy is too difficult for the evolution process to discover directly. This paper proposes a new approach that performs incremental evolution in two directions: from complex system to sub-systems and from sub-systems back to complex system. In this approach, incremental evolution gradually decomposes a complex problem into some sub-tasks. In a second step, we gradually make the tasks more challenging and general. Our approach automatically discovers the sub-tasks, their sequence as well as circuit layout dimensions. Our method is tested in a digital circuit domain and compared to direct evolution. We show that our bidirectional incremental approach can handle more complex, harder tasks and evolve them more effectively, then direct evolution.
{"title":"Bidirectional incremental evolution in extrinsic evolvable hardware","authors":"T. Kalganova","doi":"10.1109/EH.2000.869343","DOIUrl":"https://doi.org/10.1109/EH.2000.869343","url":null,"abstract":"Evolvable Hardware (EHW) has been proposed as a new technique to design complex systems. Often, complex systems turn out to be very difficult to evolve. The problem is that a general strategy is too difficult for the evolution process to discover directly. This paper proposes a new approach that performs incremental evolution in two directions: from complex system to sub-systems and from sub-systems back to complex system. In this approach, incremental evolution gradually decomposes a complex problem into some sub-tasks. In a second step, we gradually make the tasks more challenging and general. Our approach automatically discovers the sub-tasks, their sequence as well as circuit layout dimensions. Our method is tested in a digital circuit domain and compared to direct evolution. We show that our bidirectional incremental approach can handle more complex, harder tasks and evolve them more effectively, then direct evolution.","PeriodicalId":432338,"journal":{"name":"Proceedings. The Second NASA/DoD Workshop on Evolvable Hardware","volume":"62 20","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133523540","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}
Fault tolerance has always been a standard feature of electronic systems intended for long-term missions. However, the high complexity of modern systems makes the incorporation of fault tolerance a difficult task. Novel approaches to fault tolerance can be achieved by drawing inspiration from nature. Biological organisms possess characteristics such as healing and learning that can be applied to the design of fault-tolerant systems. This paper extends the work on bio-inspired fault-tolerant systems at the University of York. It is proposed that by combining embryonic arrays with an immune inspired network, it is possible to achieve systems with higher reliability.
{"title":"Embryonics+immunotronics: a bio-inspired approach to fault tolerance","authors":"D. Bradley, C. Ortega-Sanchez, A. Tyrrell","doi":"10.1109/EH.2000.869359","DOIUrl":"https://doi.org/10.1109/EH.2000.869359","url":null,"abstract":"Fault tolerance has always been a standard feature of electronic systems intended for long-term missions. However, the high complexity of modern systems makes the incorporation of fault tolerance a difficult task. Novel approaches to fault tolerance can be achieved by drawing inspiration from nature. Biological organisms possess characteristics such as healing and learning that can be applied to the design of fault-tolerant systems. This paper extends the work on bio-inspired fault-tolerant systems at the University of York. It is proposed that by combining embryonic arrays with an immune inspired network, it is possible to achieve systems with higher reliability.","PeriodicalId":432338,"journal":{"name":"Proceedings. The Second NASA/DoD Workshop on Evolvable Hardware","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127322150","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":"Proceedings the second NASA/DoD workshop on evolvable hardware","authors":"J. Lohn","doi":"10.1109/eh.2000.869336","DOIUrl":"https://doi.org/10.1109/eh.2000.869336","url":null,"abstract":"","PeriodicalId":432338,"journal":{"name":"Proceedings. The Second NASA/DoD Workshop on Evolvable Hardware","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133445521","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：