Situated and Embodied Evolution in Collective Evolutionary Robotics

合集下载

从翻译能力到译者素养_翻译教学的目标转向

１. 翻译能力20世纪70年代以来，翻译能力研究一直是过程研究领域的重点课题之一。

学术界基于不同理论范式、从不同视角对翻译能力这一关键概念进行了旷日持久的探索，形成了自然观、要素观、最简观和认知观，以期揭示翻译能力的本质属性和核心内涵，进而为翻译教学提供理论支持与实践依据。

１.1 自然观乔姆斯基的语言－行为模型对早期的翻译能力研究产生了重要影响。

威尔斯、哈瑞斯、图里等学者从双语视角对翻译能力进行了研究，总体上认为翻译能力衍生于双语能力。

威尔斯指出，双语能力之间具有互补关系，共同构成翻译能力的基础（Wilss, 1976: 117-137）。

译者必须具备源语文本的分析能力和译语文本的产出能力。

翻译天性是人类的一种基本语言能力，这一观点与哈瑞斯对翻译能力的早期定位基本相似。

20世纪70年代末期，哈里斯对双语儿童的翻译能力及其发展问题进行了专门研究，认为双语者具备运用一种语言翻译另一种语言的认知机制和能力，而且这是就可成为“自然译舍伍德认为，（1）前翻译阶段）自动翻译阶段（将；（3）传通阶段（以（Harris & 双语者拥从翻译能力到译者素养：翻译教学的目标转向李瑞林西安外国语大学摘要：本文首先梳理翻译能力研究的主要成果，在反思、统合翻译能力自然观、要素观、最简观和认知观的基础上，以译者能力这一概念为切入点探讨翻译教育的目标内涵，提出了以高阶思维能力为核心的译者能力动态观和译者素养观。

本文认为，译者素养是译者素质和译者能力综合发展的结果，主要表现为译者根据翻译情境和目的建构翻译的自主性、灵活性和创造性，是译者形成专家能力和可持续发展能力的标志，译者素养应是翻译人才培养的终极目标指向。

关键词：翻译能力；译者能力；高阶思维；译者素养中图分类号：H059 文献标识码：A 文章编号：1000-873X (2011) 01-0046-06存的（Toury, 1995: 241-258）。

与哈瑞斯的研究不同的是，图里认为，双语者早期的翻译是自发的，在功能上是冗余的。

化州一个名胜古迹英语作文

化州一个名胜古迹英语作文Huazhou, a city nestled in the heart of Guangdong province, China, is a treasure trove of cultural and historical riches. Among its many captivating landmarks, one that stands out is the renowned Huazhou Ancient Town. This picturesque settlement, with its well-preserved architecture and rich tapestry of traditions, offers visitors a glimpse into the region's illustrious past and the resilience of its people.The origins of Huazhou Ancient Town can be traced back to the Han Dynasty, when it served as a crucial transportation hub and commercial center. The town's strategic location, situated along the banks of the Xijiang River, made it an integral part of the vibrant maritime trade routes that connected China to the rest of the world. Over the centuries, Huazhou's influence and prosperity only grew, as it became a thriving hub of cultural exchange and a testament to the ingenuity of its inhabitants.One of the most striking features of Huazhou Ancient Town is its well-preserved architectural heritage. The town's narrow streets are lined with a harmonious blend of traditional Cantonese-stylebuildings, their intricate wooden facades and ornate details a testament to the skilled craftsmanship of the past. Visitors can wander through these winding alleys, marveling at the intricate patterns and symbols that adorn the buildings, each one a unique work of art.The centerpiece of Huazhou Ancient Town is undoubtedly the Ancestral Temple, a sprawling complex that serves as the spiritual heart of the community. This magnificent structure, with its ornate roofs, intricate carvings, and imposing presence, is a masterpiece of traditional Chinese architecture. The temple's halls and courtyards are filled with the rich scent of incense, as local residents and visitors alike come to pay their respects to their ancestors and seek guidance from the revered deities.Beyond the Ancestral Temple, Huazhou Ancient Town boasts a wealth of other historical and cultural treasures. The Guangji Bridge, a stunning stone arch bridge that spans the Xijiang River, is a testament to the engineering prowess of the town's builders. The bridge's elegant design and strategic placement have made it a beloved landmark, serving as a gathering place for locals and a popular spot for photographers.The town's vibrant markets and artisanal workshops are another draw for visitors. Here, one can find a dazzling array of traditionalhandicrafts, from delicate embroidery to intricate wood carvings. Skilled artisans ply their trades, passing down techniques that have been honed over generations, creating unique and captivating pieces that reflect the rich cultural heritage of Huazhou.The rhythms of daily life in Huazhou Ancient Town are deeply intertwined with the town's history and traditions. Locals gather in the town's teahouses to sip fragrant brews, engage in lively discussions, and play traditional games like mahjong. The sound of Cantonese opera, a beloved art form in the region, can be heard wafting through the streets, as performers bring the stories of the past to life on stage.One of the most remarkable aspects of Huazhou Ancient Town is the way it has managed to preserve its unique identity and traditions in the face of rapid modernization. Despite the pressures of urbanization and the allure of progress, the town's residents have fiercely guarded their cultural heritage, ensuring that the essence of Huazhou endures.This commitment to preserving the past is evident in the town's various cultural festivals and celebrations. The Lantern Festival, for instance, is a vibrant event that draws crowds from far and wide, as the town's streets are adorned with a dazzling array of colorful lanterns, each one a work of art. The Dragon Boat Festival, anothercherished tradition, sees the town's residents take to the waters of the Xijiang River, racing in brightly painted boats and honoring the legacy of the legendary poet Qu Yuan.As one wanders through the streets of Huazhou Ancient Town, it becomes clear that this is a place that has weathered the storms of time, yet emerged stronger and more resilient. The town's enduring spirit, embodied in its architecture, traditions, and the warmth of its people, is a testament to the enduring power of cultural identity and the importance of preserving our shared heritage.In a world that is rapidly changing, Huazhou Ancient Town stands as a beacon, reminding us of the timeless values that have sustained human civilization. It is a place that invites us to slow down, to immerse ourselves in the rich tapestry of history, and to connect with the timeless rhythms of a culture that has endured for centuries. Whether you are a history buff, a lover of architecture, or simply someone in search of a unique and authentic cultural experience, Huazhou Ancient Town is a destination that will leave an indelible mark on your heart and mind.。

Philosophical Transactions of the Royal Society London – A (2003) The Role of Social and C

The Role of Social and Cognitive Factors in the Emergence of Communication: Experiments in Evolutionary RoboticsDavide Marocco1,31 University of Calabria, Centro Interdipartimentale della Comunicazione Arcavacata di Rende, 87036Cosenza, Italydavidem@r.itAngelo Cangelosi22University of PlymouthInstitute of Neuroscienceand School of ComputingDrake Circus, PL4 8AAPlymouth, UKacangelosi@Stefano Nolfi33National Research CouncilInstitute of Cognitive Scienceand Technologies,Viale Marx 15, 00137Rome, Italynolfi@r.itAbstractEvolutionary robotics is a biologically inspired approach to robotics that is advantageous to studying the evolution of language. A new model for the evolution of language is presented. This model is used to investigate the interrelationships between communication abilities, namely linguistic production and comprehension, and other behavioral skills. For example, the model supports the hypothesis that the ability to form categories from direct interaction with an environment constitutes the ground for subsequent evolution of communication and language. A variety of experiments, based on the role of social and evolutionary variables in the emergence of communication, are described.1. IntroductionThe communication between autonomous agents, be they robots or simulated virtual agents, has recently attracted the interest of researchers from different fields. In engineering, the design and evaluation of communication systems is interesting due to its practical applications for agent-agent interaction and also for human-agent and human-robot communication (e.g. Lauria et al., 2002). For cognitive scientists, the development of computational models for the evolution of language permits the investigation of the role of sensorimotor, cognitive, neural and social factors in the emergence and establishment of communication and language (Cangelosi & Parisi, 2002).Studies on the emergence of communication are often based on synthetic methodologies such as adaptive behavior and artificial life (Steels, 1997; Kirby, in press). A group of autonomous agents interact via language games to exchange information about the external environment. Their coordinated communication system is not externally imposed by the researcher, but emerges from the interaction between agents. In such models, the levels of detail of the representation of the agents and of their environment can vary significantly. This constitutes a continuum between abstract point models, at one end, and situated, embodied robots at the other. At one extreme, only the essential communicative properties of the agents and the environment are simulated. For example, the environment can consist of a list of abstract “meanings”, and the agent consists of a function, or rule set, that maps these meanings to signals (e.g. Kirby, 2001; Oliphant, 1999). This approach is useful when one wants to study the dynamics of the auto-organization of lexicons and syntax and its dependence on single, pre-identified factors. An intermediate approach to language evolution is based on grounded simulation models (Harnad, 1990). The agents’ environment is modeled with a high degree of detail upon which emergent meanings can be directly grounded. Each simulated agent has a set of sensorimotor, cognitive and social abilities that allow it to build, through interaction, a functional representation of the environment and use it to communicate (e.g. Cangelosi, 2001; Cangelosi & Harnad, 2000; Hazlehurst & Hutchins, 1998). This type of models supports the investigation of the interaction amongst various abilities of the agents for the emergence of language and the grounding of communication symbols in the environment and the agent’s behavior.At the other end of the continuum, the communicative behavior of embodied and situated robots results from the dynamical interaction between its physical body, the nervous and cognitive system and the external physical and social environment (Beer, 1995). For example, robots can interact and communicate among themselves (e.g. Steels & Vogt, 1997; Quinn, 2001), with virtual Internet agents (Steels, 1999) and with humans (Steels & Kaplan, 2000). Such an approach permits the study of the interaction between the different levels of a behavioral system, that is from sensorimotor coordination to high-level cognition and social interaction.Amongst the robotic approaches to studying adaptive behavior, evolutionary robotics (Nolfi & Floreano, 2002) offers a series of advantages. Through evolutionary experiments, artificial organisms autonomously develop their behavior in close interaction with their environment. The main advantages of this approach are: (a) it involves systems that are embodied and situated (Brooks, 1991; Pfeifer and Scheier, 1999), and (b) it is an ideal framework for synthesizing robots whose behavior emerge from a large number of interactions among their constituent parts. This can be explained by considering that, in evolutionaryexperiments, robots are synthesized through a self-organization process based on random variation and selective reproduction where the selection process is based on the behaviors that emerge from the interactions among the robot's constituent elements and between these elements and the environment. This allows the evolutionary process to freely exploit interactions without the need to understand in advance the relation between interactions and emerging properties as it is necessarily required in other approaches that rely more on explicit design.For these reasons the evolutionary robotics approach has been successfully applied to the synthesis of robots able to exploit sensorimotor coordination (Nolfi, 2002); on-line adaptation (Nolfi and Floreano, 1999); body and brain co-evolution (Lipson and Pollack, 2000); competing and cooperative collective behaviors; (Nolfi and Floreano, 1998, Martinoli, 1999; Baldassarre, Nolfi, and Parisi, 2002).These advantageous aspects of evolutionary robotics are of particular importance for modeling the evolution of language and communication. Sensorimotor coordination, social interaction, evolutionary dynamics and the use of neural systems can all have a potential impact in the emergence of coordinated communication. In this paper, new experiments are presented that study the emergence of communication in evolutionary robotics models. They are based on recent work by Nolfi and Marocco (2002) for the emergence of sensorimotor categorization. Nolfi and Marocco evolved the control system of artificial agents that are asked to categorize objects with different shapes on the basis of tactile information. Each agents uses proprioceptive information to actively explore objects using a three-segment arm. In addition, the agent uses the activation of one output node of its neural network controller as input. Agents are selected only for their performance in discriminating (categorizing) the objects using this unit, not for their ability to explore them. This results in the emergence of an active tactile exploration strategy that differentiate between objects of different shapes. Nolfi and Marocco’s model is an example of explicit self-categorization.In this new model, the robotic agents share the explicit categorization of objects. That is, the activation of the output nodes is the signal (“name”) sent to another agent to instruct it on what to do with the object. Agents will be selected on their ability to manipulate objects correctly, not on their (linguistic) ability to name them correctly. A variety of experiments will test the role of different social and evolutionary variables. These will be used to analyze the role of sensorimotor, social and cognitive factors in the emergence of communication. The direct relations between behavioral and communication abilities, such us language production and comprehension, will also be discussed. 2. MethodThe behavior of each agent consists of exploration within the environment, on the basis of tactile information, and the communication, about the type of objects that are in it. The environment consists of an open three-dimensional space in which one of two different objects is present in each epoch (Figure 1). The two objects used in this simulation are asphere and a cube.Figure 1 – The arm and a spherical object.Figure 2 – A schematic representation of the arm.Agents are provided with a 3-segments arm with 6 degrees of freedom (DOF) and extremely course touch sensors (see Figure 2). Each segment consists in a basic structure of two cylindrical bodies and two joints. This is replicated for three times. The basic structure consists of a shorter body of radius 2.5 and length 3 and a longer body of the same radius and length 10 for the first two segments. The length of the third segment is 5. This shorter segment represents a fingerless hand. The two bodies of each segment are connected by means of a joint (i.e. the Joint E in the Figure) that allows only one DOF on axis Y, while the shorter body is connected at the floor, or at the longer body, by means of a joint (i.e. the Joint R) that provides one DOF on axis X. In practice, the Joint E allows to elevate and lower the connected segments and the Joint R allows to rotate them in both direction. Notice that Joint E is free to moves only in a range between 0 and π/2, just like a human arm that can bend the elbow solely in a direction. The rangeof Joint R is [–π/2, +π/2]. Gravity is {0, –1, 0}. Each actuator is provided with a corresponding motor that can apply a maximum force of 50. Therefore, to reach every position in the environment the control system has to appropriately control several joints and to deal with the constraints due to gravity.The sensory system consists of a simple contact sensor placed on each longer body that detects when this body collides with another, and two proprioceptive sensors that provide the current position of each joint.The controller of each individual consists of an artificial neural networks with 11 sensory neurons connected to 3 hidden neurons. These connect with 8 output neurons. The first 9 sensory neurons encode the angular position (normalized between 0.0 and 1.0) of the 6 DOF of the joints and the state of the three contact sensors located in the three corresponding segments of the arm. The other 2 sensory neurons receive their input from the other agents. The first 6 motor neurons control the actuators of the corresponding joints. The output of the neurons is normalized between [0, +π/2] and [–π/2, +π/2] in the case of elevation or rotational joints respectively and is used to encode the desired position of the corresponding joint. The motor is activated so to apply a force (up to 50) proportional to the difference between the current and the desired position of the joint. The last 2 output neurons encode the signal to be communicated to the other agents. This works as a small winner-takes-all cluster, where the neuron with the highest activation is set to 1 and the other to 0.The activation state of internal neurons was updated accordingly to the following equations (output neurons were updated according to the logistic function):+=iij j jO w t()()1)1(11−−−+−+=j A j t jj j eO O ττ(1) 10≤≤j τWith Aj being the activity of the j th neuron (or the state of the corresponding sensor in the case of sensory neurons), tj the bias of the j th neuron, Wij the weight from the i th to the j th neuron, Oi the output of the i th neuron. Oj is the output of the j th neuron, τj the time constant of the j th neuron.Each individual was tested for 36 epochs, each epoch consisting of 150 sensorimotor cycles. At the beginning of each epoch the arm is fully extended. A spherical or a cubic object is placed in a random selected position in front of the arm. The position of the object is randomly selected between the following intervals: 15.0 <= X <= 25.0; Y = 7.5; –5.0 <= Z <= 5.0). The object is a sphere (15 units in diameter) during even epochs and a cube (15 units in side) during odd epochs so that each individual has to discriminate the same number of spherical and cubic objects during its lifetime.In addition to the proprioceptive information, agents also receive in input a 2-bit signal produced by some other agent in the population, such as the parent or any agent from the population (linguistic comprehension task). The protocol of interaction and communication between agents was systematically varied and is analyzed in section 3.Before they act as speaker, agents undergo a linguistic production task. That is, each agent is put in the environment and asked to interact with the object. The value of the two output neurons in the last cycle of the epoch is saved and used as the signal produced to “name” the object. A genetic algorithm is used to evolve the behavior of agents. The genotype of each agent consists of 81 parameters that include 67 weights, 11 biases, and 3 time constants. Each parameter is encoded with 8 bits. Weights and biases are normalized between –5.0 and 5.0, time constants are normalized between 0.0 and 1.0.The fitness rewards the behavior of the agent with the current object in the environment. Good communication behavior does not produce any fitness gain for the speaker. Following the behaviors evolved in Nolfi & Marocco’s (2002) simulation, the agent has to touch and stay in contact with one object (the sphere) and has to avoid as much as possible to touch the other object (cube). The fitness of individuals is computed by summing the number of cycles in which the agent touches the sphere or does not touch the cube. Fitness scores decrease for each cycle the agent touches the cube or when it does not touch the sphere.A population of 80 agents is used in each simulation. During selection, the 20 agents with the highest fitness (i.e. behavioral performance) reproduce and each make 4 offspring. The genotype of each offspring is then subject to mutation with an overall probability of 2%. That is, each bit has a 2% probability of being mutated, by generating a random binary value. There is generational overlap between the population of parents and that of new offspring. The first will only act as speakers and cannot reproduce anymore. The population of new offspring will be subject to the fitness test and will reproduce at the end of their lifetime. Evolutionary simulation of embodied robotic agents can be time consuming and computationally expensive. To reduce the time necessary to test individual behaviors and to model the real physical dynamics as accurately as possible, the rigid body dynamics simulation SDK of Vortex TM was used 1. This was linked to the EvoRobot simulator (Nolfi, 2000).3. ResultsThe simulation model was used to run a series of experiments on the role of various social and evolutionary variables in the emergence of shared communication. The first independent variable refers to the selection of speakers (SPEAKER) with two levels: Parent or All. In the first case, each agent receives communication signals only from its own parent. In the second level of the variable, each agent1/products/vortex/can receive signals from any individual of the previous population. This factor is aimed at investigating the role of different social groups of speakers in facilitating shared communication.The second independent variable manipulated during experiments consists in the time in which communication is allowed (COMMUNICATION) with two levels: From_0 and From_50. In the first case, agents were allowed to communicate from the initial random generation. In the second level of the variable, agents start to communicate between themselves only at generation 50, i.e. after they have evolved a good ability to touch/avoid the two objects. Through this variable it will be possible to investigate the initial behavioral and cognitive abilities necessary to evolve communication.For each of the 4 conditions (2 SPEAKER × 2 COMMUNICATION), 10 replications were executed, by changing the initial random population. Fifty generations were necessary to pre-evolve an optimal behavior of object manipulation to be used in the From_50 conditions. Table 1 reports the communication success in each condition in terms of good populations and percentage of good speaker in the population. The criterion for deciding whether a population has successfully evolved communication depends on the fact that, at the last generation, at least 50% of agents produce two signals that differentiate the two objects.Table 1 – Data on the emergence of communication in each experimental condition. The first line contains the number of populations (out of 10) where communication emerged. The second line contains the average percentage of good speakers for the 10 replications and the average for the best performing population (value between brackets).SPEAKER COMMUNICATIONFrom 0COMMUNICATIONFrom 50Parent# good pops % speakers (best pop)527% (75%)763% (100%)All# good pops % speakers (best pop)7% (20%)5% (27%)The results of the number of populations that evolve shared communication clearly show that it is only when the parents act as the speakers there is a selective pressure for the emergence and preservation of a shared communication system. In particular, 7 populations out of 10 reach a stable communication system when language is introduced after agents have learned to use both objects. Figure 3 shows the fitness curves and the proportion of good speaker in the best seed of the condition From_50 - Parent speaker.When communication is introduced directly from the initial random population, the probability of evolving a good language, together with a good behavior, is lower (5 populations out of 10). This advantage for evolving languages after the basic behavioral skills have evolved is similar to that observed by Cangelosi & Parisi (2001) in a grounded simulation model on the emergence of verbs and nouns.When agents listen to all individuals of the previous generation, no stable communication exists in the last generations. In fact, during evolution good lexicons sometimes emerge for a short time, but they are not maintained or further developed by the whole population. A temporary good lexicon is defined as the case in which at least 20% of agents use two different signals to name the two objects. In 8 of the 10 From_50 - All speaker populations, such temporary appearances of good signal production is observed. Figure 4 shows the best population in the From_50 - All speaker conditions. Here the longest period of good production only lasts for 17 generations,with a maximum peak of best language at 41%.Figure 3 – Data for the best population of the condition Parentspeaker - From_50.Figure 4 – Data for the best population in condition All speakers - From_50.The lexicon produced by agents in successful replications has been tested to investigate whether individuals actually use this language in a meaningful way, i.e. avoid the cube when the signal produced in response to the cube is used, and touch the sphere when the other signal is used. Figure 5 shows the behavior of an agent that interacts with the cube with or without language. This tests the linguistic comprehension ability of agents. The pictures on the left column (Figure 5 - left) show the behavior of the agent when no input signal is used. The agent needs to touch the cube, at least once (in cycle 95), to identify it as a cubeand then retract from it. The pictures on the right (Figure 5 - right) show the behavior of the agent when the signal “10” is used as additional input. This signal is produced by the parent organism at the end of the interaction with a cube. During this scene, the agent does not need to touch the cube at all because the signal “10” identifies it as a cube. The meaning of “10” can be interpreted as “cube”2, because the listener treats the object as a cube, and the speaker produces it after its interaction with a cube. When the signal “01” is used, the agent touches the object regardless of its shape. Inthis case, “01” has the meaning of “sphere”.Figure 5 – Agent’s interaction with the cube and test of linguistic understanding ability. Left column: Only the proprioceptive input is given to the agent. Right column: An additional communication signal is given as input. This is produced by another agent at the end of its interaction with a cube. Figures from the best individual of a From_50 - Parent speaker population.Fitness data shows that final scores in the 4 experimental conditions reflect the pattern of results on the emergence of successful communication. The two conditions with Parent speakers reach the highest fitness scores, with a significant2This signal can also be interpreted as the verb avoid , instead of as the noun cube . In fact, in this model it is not possible to distinguish between syntactic word classes (cf. Cangelosi & Parisi 2001 and Cangelosi 2001 for a discussion)advantage for the From_50 populations (e.g. average fitness of best individuals = 0.55; fitness peak in best population = 0.72) versus the From_0 population (average = 0.45, peak = 0.66). The baseline for the behavior without communication is the fitness at generation 50 of the From_50 simulation, before agents start to communicate (average = 0.44, peak = 0.52). Consider that the maximum hypothetical fitness score is 1. This can never be reached because, for example, at the beginning of each epoch some negative fitness cycles are always necessary for agents to reach the spherical object and start gaining fitness.4. DiscussionThere are several issues that can be discussed regarding these results, and what we can learn from the model. A series of questions will be used to analyze the results.Question 1: Is there any benefit to be in a population wheregood communication has emerged?Question 2: Is there any direct advantage to evolving agood linguistic comprehension ability?To answer the first question, it is possible to compare the fitness results in the simulations where no shared communication emerged, and those where good communication systems evolved. The condition in which communication emerged more frequently (From_50, Parent speaker) will be used as example. In this condition, 7 populations evolved good languages, whilst 3 did not. Figure 6 shows the average fitness of the good communication populations (thick lines) and that of the no communication populations (thin lines). The chart clearly shows that agents who use communication reach fitness values that are higher that those not communicating. This is true both for the fitness of the best individual and for that of the whole population. For example, at the final generation the average fitness of the 7 successful communication replications is 0.35, while it is 0.21 for the 3 unsuccessful populations. Moreover, the fitness in these 3 populations remains relatively constant during the simulation. In the first 50 generations after communication is permitted (i.e. from 50 to 100), there is no increase and the average fitness at generation 100 is very similar to that at generation 50. In the remaining generations, the agents gain some extra fitness points, which are due to the continuation of the evolutionary algorithm search.The extra fitness gain in populations that evolve communication is easily explained by the direct benefits for the behavior (i.e. fitness) of using two different signals: one for the cube, and one for the sphere. As already shown in Figure 5, during the interaction with a cube the input of its “name” produces significant improvements to behavioral performance. Agents do not need to touch the object to recognize it, and therefore do not lose fitness due to such exploratory behavior. In addition, they gain fitness in every cycle. There is also some benefit for the use of the signal for the sphere. If an agent initially is told that there is a spherical object in the environment, it can go directlytowards the object and touch it, without having to use some interaction cycles for recognizing the object as a non cube.The previous explanations also answer the second question, since they identify a direct adaptive advantage for evolving a good comprehension ability.Figure 6 – Average fitnesses of the conditions From_50 - Parent speaker. Thick lines refer to the average fitness of the 7 replications where good communication emerged (continuous line for the best agent and dotted line for the average of all agents). Thin lines refer to the average fitness of the 3 replications where no shared communication emerged.Question 3: Is there any “direct” advantage to evolving good linguistic production abilities?This question is more difficult to answer. In fact, there seems to be no direct fitness advantage to the agents to speaking well. Individuals only update their fitness when they hear others speaking. When agents act as speakers, some have already reproduced, whilst the others have not been selected at all. In the condition Parent speaker, agents only speak to their own children. Therefore, the kinship relationship can partially explain this apparent altruistic behavior and the indirect fitness gain for the common genes shared by the parent and its offspring (e.g. Ackley & Littman, 1994). The benefits of kin selection can also explain the successful evolution of communication in the Parent speaker versus the All speaker conditions. However, there is another important phenomenon to be considered. In the Parent speaker conditions, the linguistic input to each listener is constant, since its parent will always use the same signal for the same object. In addition, when the parent is a good speaker (i.e. it uses two different signals to refer to the two objects), its signals are more reliable. The child can then try to use them to improve its fitness performance. In the All speaker conditions, the high variability of the linguistic input coming from all agents of previous generation can be too unreliable, and agents will tend to ignore it.In the All speaker conditions, some communication abilities also emerge, although the number of good speakers never reaches the critical amount needed to allow it to remain stable until the end of the simulation (cf. Figure 4).In addition, in the Parent speaker conditions, there are threecases when shared communication does not evolve. According to the altruistic, kin selection explanation, allParent speaker populations should evolve communicationbecause of it indirect adaptive advantage. The fact that this does not always happen raises the issues of understanding the relation between linguistic comprehension/productionabilities and other behavioral/cognitive abilities (question4), and the identification of factors that cause and favor the emergence of shared communication (question 5). First, thedata in Table 1 indicates that it is easier to evolve goodcommunication when language is introduced after the pre-evolution of good behavioral capacities (7 out of 10 populations) than when agents are allowed to communicatefrom the initial generation (5 out of 10 seeds). In addition,the onset of effective communication (i.e. when at least 20% of agents speak well) is much earlier in the From_50 populations (on average after 16 generations) that in theFrom_0 simulations (on average after 41 generations). Thisdata is consistent with Cangelosi and Parisi’s (2001) model on the evolution of syntactic languages. This researchshowed that agents learn languages more efficiently whencommunication is introduced after the pre-evolution of goodbehavioral skills. Effectively, the pre-evolution of good behavior “prepares” a cognitive ground upon which goodlinguistic abilities can start to develop. Analyses of thecategorical perception effects in language learning models have shown that language uses and modifies the space of similarities between members of different perceptual andlinguistic categories (Cangelosi & Harnad, 2000). Question 4: What is the relation between comprehension,production and behavioral abilities? Question 5: What are the underlying factors that cause andfavor the emergence of communication?To understand better the relations betweencommunication abilities and behavioral skills, thecorrelations between fitness scores and a measure of the quality of produced language have been computed. Figure 7and 8 present the averages of the fitness curves, theproportions of good speakers (i.e. language index), thefitness/language correlation r all for the whole population, and the fitness/language correlation r best for the best 20agents. Figure 7 refers to the 7 successful populations of the From_50 - Parent speaker condition. Figure 8 refers to data from the remaining 3 populations without communication.For the computation of the language index based on theproportion of good speakers, an agent is classified as goodspeaker when it produces two opposite signals respectively for the two objects in at least half of the 36 epochs. ThePearson r correlations index was used.Overall, the two figures show that the correlationbetween the fitness of all agents and their language production index is positive and quite high (r all ≈ 0.5) after good communication emerges. This can explain themaintenance of good communication, since it reflects a link。

精品解析：2022年新高考全国一卷英语真题(解析版)

Daily Work/In-Class Writings and Tests/Group Work/Homework (10%)
Class activities will vary from day to day, but students must be ready to complete short in-class writings or tests drawn directly from assigned readings or notes from the previous class' lecture/discussion, so it is important to take careful notes during class. Additionally, from time to time I will assign group work to be completed in class or short assignments to be completed at home, both of which will be graded.
Grading Scale
90-100, A; 80-89, B; 70-79, C; 60-69, D; Below 60, E.
Essays (60%)
Your four major essays will combine to form the main part of the grade for this course: Essay 1= 10%; Essay 2 = 15%; Essay 3 = 15%; Essay 4 = 20%.
4.What does the author want to show by telling the arugula story?

去淄博旅游的英语作文

Visiting Zibo: A Journey of Discovery andDelightThe city of Zibo, situated in the eastern province of Shandong, China, holds a rich tapestry of cultural and natural wonders that await the eager explorer. My journeyto this charming destination was a blend of history, nature, and gastronomic delights, each element leaving a lasting impression on my heart and mind.Upon arrival, the first stop on my itinerary was the Zibo Museum of Ceramics. This museum, a testament to thecity's long-standing history in pottery making, showcasedan array of intricate and beautiful ceramic pieces. From ancient vessels to contemporary artworks, each piece was a window into the skilled craftsmanship and innovative spirit of Zibo's ceramic artists. I found myself lost in admiration, marveling at the intricate details and thedepth of tradition embodied in these works.From the museum, I ventured outdoors to explore the natural beauty of Zibo. A visit to the Taihe Waterfall wasa highlight of my trip. The soaring cliffs and the plunging water created a breathtaking sight that was both calmingand invigorating. Standing beneath the falls, I felt the refreshing mist on my face, a welcome coolness in the summer heat. The serene surroundings provided a perfect backdrop for a moment of contemplation and appreciation of nature's wonders.No trip to Zibo would be complete without a culinary adventure. The city is renowned for its delicious cuisine, and I was eager to sample the local delicacies. From the fragrant and spicy Sichuan-style dishes to the fresh seafood offerings, each meal was a treat for the senses. I particularly enjoyed the locally famous roasted lamb, its tender meat and savory spices a testament to the culinary expertise of Zibo's chefs.In addition to the food, I also found the local people to be a highlight of my visit. The warmth and friendliness of the Zibo people made me feel welcome and at home. Whether it was a chance encounter with a local artisan selling his wares on the street or a conversation with a restaurant owner sharing his family recipes, these interactions added a rich layer of authenticity to my experience.As my journey in Zibo drew to a close, I realized that this city had more than fulfilled my expectations. It was a place where history and nature converged, where traditional crafts and modern conveniences coexisted, and where the warmth of human interaction enhanced every experience. Zibo is a city that invites exploration, offering something new and wonderful to discover at every turn.My visit to Zibo was not just a trip, but a journey of discovery and delight. It left me with a renewed appreciation for the beauty and diversity of China's cultural and natural landscapes, and a lasting memory of the warmth and charm of this remarkable city.**淄博之旅：探索与愉悦的旅程**位于中国东部山东省的淄博市，拥有丰富多彩的文化和自然奇观，吸引着渴望探索的旅行者。

tpo35三篇阅读原文译文题目答案译文背景知识

tpo35三篇阅读原文译文题目答案译文背景知识阅读-1 (1)原文 (2)译文 (5)题目 (8)答案 (17)背景知识 (18)阅读-2 (21)原文 (21)译文 (24)题目 (27)答案 (36)背景知识 (36)阅读-3 (39)原文 (39)译文 (43)题目 (46)答案 (54)背景知识 (55)阅读-1原文Earth’ s Age①One of the first recorded observers to surmise a long age for Earth was the Greek historian Herodotus, who lived from approximately 480 B.C. to 425 B.C. He observed that the Nile River Delta was in fact a series of sediment deposits built up in successive floods. By noting that individual floods deposit only thin layers of sediment, he was able to conclude that the Nile Delta had taken many thousands of years to build up. More important than the amount of time Herodotus computed, which turns out to be trivial compared with the age of Earth, was the notion that one could estimate ages of geologic features by determining rates of the processes responsible for such features, and then assuming the rates to be roughly constant over time. Similar applications of this concept were to be used again and again in later centuries to estimate the ages of rock formations and, in particular, of layers of sediment that had compacted and cemented to form sedimentary rocks.②It was not until the seventeenth century that attempts were madeagain to understand clues to Earth's history through the rock record. Nicolaus Steno (1638-1686) was the first to work out principles of the progressive depositing of sediment in Tuscany. However, James Hutton (1726-1797), known as the founder of modern geology, was the first to have the important insight that geologic processes are cyclic in nature. Forces associated with subterranean heat cause land to be uplifted into plateaus and mountain ranges. The effects of wind and water then break down the masses of uplifted rock, producing sediment that is transported by water downward to ultimately form layers in lakes, seashores, or even oceans. Over time, the layers become sedimentary rock. These rocks are then uplifted sometime in the future to form new mountain ranges, which exhibit the sedimentary layers (and the remains of life within those layers) of the earlier episodes of erosion and deposition.③Hutton's concept represented a remarkable insight because it unified many individual phenomena and observations into a conceptual picture of Earth’s history. With the further assumption that these geologic processes were generally no more or less vigorous than they are today, Hutton's examination of sedimentary layers led him to realize that Earth's history must be enormous, that geologic time is anabyss and human history a speck by comparison.④After Hutton, geologists tried to determine rates of sedimentation so as to estimate the age of Earth from the total length of the sedimentary or stratigraphic record. Typical numbers produced at the turn of the twentieth century were 100 million to 400 million years. These underestimated the actual age by factors of 10 to 50 because much of the sedimentary record is missing in various locations and because there is a long rock sequence that is older than half a billion years that is far less well defined in terms of fossils and less well preserved.⑤Various other techniques to estimate Earth's age fell short, and particularly noteworthy in this regard were flawed determinations of the Sun's age. It had been recognized by the German philosopher Immanuel Kant (1724-1804) that chemical reactions could not supply the tremendous amount of energy flowing from the Sun for more than about a millennium. Two physicists during the nineteenth century both came up with ages for the Sun based on the Sun's energy coming from gravitational contraction. Under the force of gravity, the compressionresulting from a collapse of the object must release energy. Ages for Earth were derived that were in the tens of millions of years, much less than the geologic estimates of the lime.⑥It was the discovery of radioactivity at the end of the nineteenth century that opened the door to determining both the Sun’s energy source and the age of Earth. From the initial work came a suite of discoveries leading to radio isotopic dating, which quickly led to the realization that Earth must be billions of years old, and to the discovery of nuclear fusion as an energy source capable of sustaining the Sun's luminosity for that amount of time. By the 1960s, both analysis of meteorites and refinements of solar evolution models converged on an age for the solar system, and hence for Earth, of 4.5 billion years.译文地球的年龄①希腊历史学家希罗多德是最早有记录的推测地球年龄的观察家之一，他生活在大约公元前480年到公元前425年。

英语作文我的旅行宜宾

Situated in the heart of Sichuan Province, Yibin, a city steeped in history and culture, beckons travelers with its captivating blend of ancient traditions and modern vibrancy. My recent sojourn in this charming locale was an immersive experience that left me enamored with its diverse landscapes, rich heritage, culinary delights, and warm hospitality. In this essay, I delve into the multifaceted aspects of my Yibin journey, painting a vivid picture of the city's allure from various perspectives.**A Tapestry of History and Architecture**Yibin's historical significance is palpable as one wanders through its streets, where ancient structures stand harmoniously alongside modern edifices. The Wuliangye Museum, a testament to the city's renowned liquor-making tradition, showcases the evolution of distillation techniques over centuries, offering a fascinating insight into Yibin's contribution to China's cultural and economic heritage. Adjacent to it, the imposing Yibin Bridge, a Qing Dynasty relic, spans the Yangtze River, symbolizing the city's strategic role as a vital transportation hub since ancient times.The Jiuweng Pagoda, nestled atop Mount Qianfo, is another architectural gem that encapsulates Yibin's historical depth. This 13-story octagonal tower, dating back to the Tang Dynasty, not only offers breathtaking panoramic views of the city but also serves as a spiritual beacon, evoking a sense of serenity and timelessness. The fusion of history, artistry, and spirituality embodied by these structures creates a captivating ambiance that transports visitors back in time.**A Symphony of Nature and Scenic Splendor**Yibin's natural beauty is a feast for the senses, with its verdant hills, glistening rivers, and tranquil lakes. A visit to the Bamboo Sea, a vast expanse of lush greenery stretching across several valleys, is a must for nature enthusiasts. The rustling bamboo groves, cascading waterfalls, and misty vistas create a mesmerizing atmosphere that inspired countless poets and artists throughout history. The Liangshan Yi Autonomous Prefecture, bordering Yibin,offers further opportunities for eco-tourism, with its majestic mountains, ethnic minority villages, and diverse wildlife.The confluence of the Min and Yangtze Rivers in Yibin is a geological marvel, best appreciated from the scenic Shuangliu Park. The sight of these mighty rivers merging, their distinct hues blending into a unified flow, is both awe-inspiring and humbling. Moreover, the Yangtze Three Gorges Dam, a short distance upstream, is an engineering marvel that underscores China's commitment to harnessing clean energy while preserving the region's ecological balance.**A Gastronomic Odyssey**Yibin's culinary scene is a vibrant reflection of its geographical location and cultural diversity. The city is renowned for its hot pot, a fiery, flavorful dish that embodies the bold and spicy essence of Sichuan cuisine. Dining at local hot pot establishments like Huangcheng Laoma or Deyi Xiaolong, one can savor a myriad of ingredients, from tender meats and fresh vegetables to exotic mushrooms and handmade noodles, all simmering in a rich, chili-laden broth.Beyond hot pot, Yibin's culinary delights extend to its street food, where one can indulge in mouthwatering snacks like Zhong Shui Jiao (steamed dumplings), Guokui (spicy meat-filled baked buns), and Liangfen (cold mung bean jelly). The city's signature liquor, Wuliangye, made from five types of grains, is another gastronomic highlight, often enjoyed during meals or as a toast to friendship and good fortune.**Warmth of Hospitality and Cultural Immersion**The people of Yibin are known for their warmth and hospitality, which adds a personal touch to every traveler's experience. Whether engaging in friendly banter with locals at a bustling night market, participating in a traditional tea ceremony at a serene teahouse, or learning calligraphy from a skilled artisan, encounters with the locals offer a genuine glimpse into the city's vibrant culture and way of life.Furthermore, Yibin's annual festivals, such as the Lantern Festival and Dragon Boat Festival, provide opportunities for immersive cultural experiences.These events showcase vibrant folk performances, traditional arts and crafts, and festive delicacies, allowing visitors to partake in the city's age-old customs and celebrations.**Conclusion: A Journey Unforgettable**In conclusion, my journey through Yibin was a captivating exploration of a city that seamlessly blends history, nature, gastronomy, and culture. From the ancient architecture that whispers tales of the past to the mesmerizing landscapes that stir the soul, from the fiery flavors that tantalize the taste buds to the warm hospitality that touches the heart, Yibin offers a multifaceted travel experience that is truly unforgettable. It is a destination that invites travelers to delve deep into its rich tapestry, leaving them enriched, inspired, and longing to return.Although this essay exceeds the word count requirement, it does so to provide a comprehensive and detailed account of the enchanting city of Yibin, capturing its essence from multiple angles and ensuring a high-quality, in-depth analysis as per your request.。

新高考英语二轮复习攻破新题：阅读理解之说明文(2

28. The author uses the question underlined in Paragraph 1 to ________.
A. illustrate an argumentB. highlight an opinion
C. introduce the topicD. predict the ending
More researchers, policymakers and representatives from the food industry must learn to look beyond their direct lines of responsibility and adopt a systems approach. Crystal knew that visions alone don’t produce results, but concluded that “we’ll never produce results that we can’t envision”.
【29题详解】细节理解题。由文章第三段“This shows that we have some way to travel before achieving the first objective of systems t hinking - which,in this example, is to identify more constituent parts of the nutrition system.(这表明，在实现系统思考的第一个目标之前，我们还有一段路要走——在本例中，这是为了确定营养系统的更多组成部分。)”可知，实现系统思维的第一个目标还有一段路需要走，现尚未实现。故选A项。
C. Machine learning can solve the nutrition problem.

1、下载文档前请自行甄别文档内容的完整性，平台不提供额外的编辑、内容补充、找答案等附加服务。
2、"仅部分预览"的文档,不可在线预览部分如存在完整性等问题,可反馈申请退款(可完整预览的文档不适用该条件!)。
3、如文档侵犯您的权益，请联系客服反馈,我们会尽快为您处理(人工客服工作时间：9:00-18:30)。

Situated and Embodied Evolution in Collective Evolutionary Robotics Yukiya USUI Takaya ARITAGraduate School of Human Informatics,Nagoya UniversityFuro-cho,Chikusa-ku,Nagoya464-8601,JapanE-mail:{yukiya@create,ari@info}.human.nagoya-u.ac.jpAbstractEvolutionary robotics is a challenging technique for creation of autonomous robots based on the mechanism of Darwinian evolution.In the con-ventional evolutionary robotics,the“simulate-and-transfer”method has been adopted.We believe that the most likely candidate methodology in evolutionary robotics for near future is“Situated and Embodied Evolution”,in which real robots in real world evolve based on the interactions with actual environment and real robots.It becomes important when realizing Sit-uated and Embodied Evolution to decentralize the al-gorithm for evolution computation,because it could make implementation of eﬃcient systems easier and could accelerate diversiﬁcation in robot behavior.This paper proposes a distributed and asynchronous genetic algorithm forﬂexible and eﬃcient robotic systems that realize Situated and Embodied Evolution.This pa-per also reports on the performance of Situated and Embodied Evolution based on the results of the pre-liminary experiments on the robotic system we have implemented.Keywords:Situated and embodied evolution, Evolutionary robotics,Genetic algorithm.1IntroductionEvolutionary robotics is a challenging technique for creation of autonomous robots based on the mechanism of Darwinian evolution[1].In the con-ventional evolutionary robotics,the“simulate-and-transfer”method has been adopted(Figure1(a)). However,several issues are increasingly problematic for the method.1)It is very diﬃcult or takes long time to simulate complex behavior of robots and complex environment.2)It is necessary to model the environment every time when a new task is given.3)Scalability to the number of the robots is poor in case of the systems with a population of robotshaving Figure1:Schematic diagram for evolution of robots: (a)“Simulate-and-transfer”method,(b)“1genome per robot”method,(c)Proposed method.complex interaction among them.We believe that the most likely candidate method-ology in evolutionary robotics for near future is“Sit-uated and Embodied Evolution”,in which real robots in real world evolve based on the interactions with actual environment and real robots.It becomes im-portant when realizing Situated and Embodied Evolu-tion to decentralize the algorithm of evolution(genetic algorithm),because decentralization of evolutionary computation could make implementation of eﬃcient systems easier and could accelerate diversiﬁcation in robot behavior.Very few studies regarding Situated and Embod-ied Evolution have been conducted.Among them, Watson et al.proposed a method to realize Situated and Embodied Evolution based on a motivation that is similar to ours described above[2].They adopted a straightforward method for evolutionary computation, in which each robot represents one individual and pop-ulation share their genetic information by transmitting information among them when they encounter(Fig-ure1(b)).However,the progress of evolution in this method directly depends on the number of the robots and the frequency of encounter with other robots.This paper proposes a distributed and asyn-chronous genetic algorithm forﬂexible and eﬃcient robotic systems with adequate scalability that realize Situated and Embodied Evolution.There are two lev-els of optimization in this method(Figure1(c)).There is transmission of good genes among robots when they encounter.Also,each robot executes a genetic algo-rithm within itself by emulating many“virtual indi-viduals”based on time-sharing.This method thus re-duces dependence of the number of the robots and of the frequency of encounter with other robots on the speed of evolution,which can realizeﬂexible and eﬃ-cient robotic systems with adequate scalability.This paper also reports on the performance of Situated and Embodied Evolution based on the results of the pre-liminary experiments on the robotic system we have implemented.2A Model for Situated and Embodied EvolutionParallelization of genetic algorithms(GA)has been discussed in theﬁeld of evolutionary computation,mo-tivated mainly by the desire to reduce the overall com-putation time.Most of the proposed parallel GAs fall into a class which has come to be called“island model”parallel GA.Island model parallel GA divides a population into subpopulations and assigns them to processing elements on a parallel or distributed com-puter.Then each subpopulation searches the optimal solution independently,and exchanges individuals pe-riodically.Our distributed genetic algorithm for Situated and Embodied Evolution can be called island model par-allel GA in that each robot has a subpopulation, searches the optimal solution,and exchange good in-dividuals.However,there is a signiﬁcant diﬀerence in our model from the conventional island model parallel GA as follows.1)Communication topology and frequency are dy-namic,which depends on the robot behavior,espe-cially encounters of robots.2)Fitness evaluation is conducted as robot behavior in real word,which needs quite long time compared with other evolutionary operations done in the robots.3)Optimal solution varies depending on the behav-ior range and physical characteristics of each robot, besides the dynamic property of theenvironments.Figure2:Evolutionary processing in each robot.Typical implementation of evolutionary computa-tion in each robot is shown in Figure2.Each robot has a“gene pool”and a“gene queue”.The gene pool has an evolved subpopulation,whose individuals are ex-pressed as genomes and sorted by theirﬁtness values.A new individual is generated by selecting(copying)2 individuals from the gene pool based on roulette wheel selection,and operating one point crossover and mu-tation.The new individual is then put into the gene queue,and waits for being evaluated.New individuals migrated from other robots are also put into the gene queue,and reevaluated in this robot,because there can be diﬀerence in their environments and physical characteristics among robots.A dequeued individual is loaded to specify the robot behavior,and after a given length of time,it is attached with theﬁtness value,and stored into the gene pool.The gene pool has a limited capacity,and therefore the evaluated in-dividuals will be discarded if theirﬁtness values are lower than the one of the worst individual in the gene pool.This mechanism realizes time sharing among many virtual individuals in each robot.Migration procedure runs independently of the above-described GA process in each robot.An in-dividual to be transmitted is selected(copied)from the gene pool based also on roulette wheel selection asynchronously.Each robot has a chance to send its selected individual every predeﬁned time interval,the timing of which is randomly decided every event.The robot sends a selected individual with following prob-ability which depends on itsﬁtness value.If(A<=C){P=50(C−AM−A)+50}(1)else if(A>C){P=50(C−SA−S)}(2)(P:Probability of transmitting,A:Averageﬁtness,M: Maximumﬁtness,S:Minimumﬁtness,C:Fitness of the selectedindividual)Figure3:Asynchronous migration of individuals.3Preliminary ExperimentsWe have implemented a minimum experimental robotic system for the purpose of evaluating the pro-posed scheme described in the previous section.We used six Khepera miniature mobile robots(Figure4). The issue of power supply also becomes important when realizing the Situated and Embodied Evolution paradigm.Our solution in the preliminary experi-ments is to adopt a power supply mechanism by which each robot moves around in aﬂoor-and-ceiling struc-ture and receives power continuously from a panto-graph located on top of it(Figure5).Also,a charging battery built in each robot backs up the mechanism. Infra-red communication is used for transmission of individuals betweenrobots.Figure4:Khepera robot(Left-Khepera+IR commu-nication turret A:Battery,B:Infra-red sensor,C:Pan-tograph,D:Infra-red emitter/receiver,E:Incremental DC motor,F:Wheel,Right-Layout of8infra-redsensors).Figure5:Experimental setup(A:Continuous power supply,B:Infra-red emitter/receiver unit,C:Power supply).We adopted a simple two-layer neural network to control the behavior of each robot(Figure6).The structure of the neural network(connection weights and the thresholds)was evolved by distributed genetic algorithm described in the previous section.In the neural network,7input nodes corresponded to6sensorinputs and a threshold,each of which was expressed by5bit genome information.There were2output nodes corresponding to right and left motor outputs. So,the length of the genome was70bits.Figure6:Relation between individual information and the structure of neural network.Robot control programs(neural networks)for an avoidance task were evolved in the preliminary experi-ments for the purpose of conﬁrming the eﬀectiveness of the model.Each individual is evaluated by the length of movement without hitting the walls or other robots as follows:fitness+=SensorO f f()(R Motor+L Motor),(3) where SensorOﬀ()returns0when two or more infra-red sensors are activated,and otherwise returns1, and R Motor and L Motor correspond to the rotation speeds of the right and left motors.Fitness value of each robot is increased at predeﬁned time intervals when there is no input from eight infra-red sensors (which means that there are no obstacles in the neigh-borhood of the robot)and at least one motor is acti-vated.The result is shown in Figure7,where the hori-zontal axis represents the total number of evaluated individuals,and the vertical axis represents theﬁt-ness.This graph shows the typical results of following 4cases:the cases when the size of the gene pool is 1(“1genome per robot method”),5and10,and the case in which there is no migration among robots and the size of the gene pool is5.Averageﬁtness of every 20individuals is plotted in each case.We can see from thisﬁgure that the case with gene pool size of5with migration shows the best performance though the op-timal size depends at least on the number of robots and the given task.It is also shown that migration Figure7:Evolution of robot behavior(Number of robots:3,Mutation rate:2%).has a large role in this scheme.In general,there can be an unexpected diﬀerence in behavior among robots in real world.Migration of good individuals can im-prove the performance of the robots with unevolved gene pool.4ConclusionWe have proposed a distributed and asynchronous genetic algorithm forﬂexible and eﬃcient robotic sys-tems with adequate scalability that realize Situated and Embodied Evolution.We have also reported on the performance of Situated and Embodied Evolution based on the results of the preliminary experiments on the robotic system we have implemented.Further experiments will include investigation of performance evaluation of the scheme targeting at more practical tasks.References[1]Stefano Nolﬁand Dario Floreano,EvolutionaryRobotics,MIT Press,2000.[2]Richard A.Watson,Sevan G.Ficici,and Jor-dan B.Pollack,“Embodied Evolution:Embody-ing an Evolutionary Algorithm in a Population of Robots,”1999Congress on Evolutionary Compu-tation,IEEE Press,335-342,1999.。