Self-sufficient autonomous robots are able to perform independent tasks while maintaining enough energy to function. We develop a self-sufficient robot control system where a cyclic genetic algorithm (GA) is used to l...
详细信息
Self-sufficient autonomous robots are able to perform independent tasks while maintaining enough energy to function. We develop a self-sufficient robot control system where a cyclic genetic algorithm (GA) is used to learn the control program for a hexapod robot equipped with a quick charge power supply. This robot uses high capacitance capacitors for its onboard power storage and a sensor system to detect power need related information. A detailed simulation is developed, to be used by a cyclic GA to learn control programs for the robot. These programs enable it to perform area coverage and periodically return to a recharging station to maintain power. In this paper, we expound on previous research and report the transfer of the complete simulated self-sufficient behavior to the physical robot and colony power supply system, where tests have been conducted to confirm the viability of our approach.
We introduce AutoMoDe: a novel approach to the automatic design of control software for robot swarms. The core idea in AutoMoDe recalls the approach commonly adopted in machine learning for dealing with the bias-varia...
详细信息
We introduce AutoMoDe: a novel approach to the automatic design of control software for robot swarms. The core idea in AutoMoDe recalls the approach commonly adopted in machine learning for dealing with the bias-variance tradedoff: to obtain suitably general solutions with low variance, an appropriate design bias is injected. AutoMoDe produces robot control software by selecting, instantiating, and combining preexisting parametric modules-the injected bias. The resulting control software is a probabilistic finite state machine in which the topology, the transition rules and the values of the parameters are obtained automatically via an optimization process that maximizes a task-specific objective function. As a proof of concept, we define AutoMoDe-Vanilla, which is a specialization of AutoMoDe for the e-puck robot. We use AutoMoDe-Vanilla to design the robot control software for two different tasks: aggregation and foraging. The results show that the control software produced by AutoMoDe-Vanilla (i) yields good results, (ii) appears to be robust to the so called reality gap, and (iii) is naturally human-readable.
We introduce FARSA, an open-source Framework for Autonomous robotics Simulation and Analysis, that allows us to easily set up and carry on adaptive experiments involving complex robot/environmental models. Moreover, w...
详细信息
We introduce FARSA, an open-source Framework for Autonomous robotics Simulation and Analysis, that allows us to easily set up and carry on adaptive experiments involving complex robot/environmental models. Moreover, we show how a simulated iCub robot can be trained, through an evolutionary algorithm, to display reaching and integrated reaching and grasping behaviours. The results demonstrate how the use of an implicit selection criterion, estimating the extent to which the robot is able to produce the expected outcome without specifying the manner through which the action should be realized, is sufficient to develop the required capabilities despite the complexity of the robot and of the task.
The field of collective robotics has been raising increasing interest in the last few years. In the vast majority of works devoted to collective robotics all interacting robots play always the same function, while les...
详细信息
The field of collective robotics has been raising increasing interest in the last few years. In the vast majority of works devoted to collective robotics all interacting robots play always the same function, while less attention has been paid to groups of collaborating robots in which different robots play different roles. In this paper we evolve a population of homogeneous robots for dynamically allocating roles through communicative interactions. In particular, we focus on the development of a team of robots in which one and only one individual (the 'leader') must differentiate its communicative behaviour from that of all the others ('non-leaders'). Evolved solutions prove to be very robust with respect to changes in the size of the group. Furthermore, both behavioural analyses and a comparison with a control condition in which robots are not allowed to move demonstrate the importance of co-adapting communicative and non-communicative behaviours, and, in particular, of being allowed to dynamically change the topology of communicative interactions. Finally, we show how the same method can be used for solving other kinds of role-allocation tasks. The general idea proposed in this paper might be used in the future for evolving general, robust, and scalable role differentiation mechanisms which can be exploited to develop non-communicative collaborative behaviours that require specialisation of roles within groups of homogeneous individuals.
We investigate the reality gap, specifically the environmental correspondence of an on-board simulator. We describe a novel distributed co-evolutionary approach to improve the transference of controllers that co-evolv...
详细信息
We investigate the reality gap, specifically the environmental correspondence of an on-board simulator. We describe a novel distributed co-evolutionary approach to improve the transference of controllers that co-evolve with an on-board simulator. A novelty of our approach is the the potential to improve transference between simulation and reality without an explicit measurement between the two domains. We hypothesise that a variation of on-board simulator environment models across many robots can be competitively exploited by comparison of the real controller fitness of many robots. We hypothesise that the real controller fitness values across many robots can be taken as indicative of the varied fitness in environmental correspondence of on-board simulators, and used to inform the distributed evolution an on-board simulator environment model without explicit measurement of the real environment. Our results demonstrate that our approach creates an adaptive relationship between the on-board simulator environment model, the real world behaviour of the robots, and the state of the real environment. The results indicate that our approach is sensitive to whether the real behavioural performance of the robot is informative on the state real environment.
Researchers in diverse fields, such as in neuroscience, systems biology and autonomous robotics, have been intrigued by the origin and mechanisms for biological robustness. Darwinian evolution, in general, has suggest...
详细信息
Researchers in diverse fields, such as in neuroscience, systems biology and autonomous robotics, have been intrigued by the origin and mechanisms for biological robustness. Darwinian evolution, in general, has suggested that adaptive mechanisms as a way of reaching robustness, could evolve by natural selection acting successively on numerous heritable variations. However, is this understanding enough for realizing how biological systems remain robust during their interactions with the surroundings? Here, we describe selected studies of bio-inspired systems that show behavioral robustness. From neurorobotics, cognitive, self-organizing and artificial immune system perspectives, our discussions focus mainly on how robust behaviors evolve or emerge in these systems, having the capacity of interacting with their surroundings. These descriptions are twofold. Initially, we introduce examples from autonomous robotics to illustrate how the process of designing robust control can be idealized in complex environments for autonomous navigation in terrain and underwater vehicles. We also include descriptions of bio-inspired self-organizing systems. Then, we introduce other studies that contextualize experimental evolution with simulated organisms and physical robots to exemplify how the process of natural selection can lead to the evolution of robustness by means of adaptive behaviors. (C) 2014 Elsevier Ireland Ltd. All rights reserved.
This paper is concerned with the problem of learning multiple skills by modular robots. The main question we address is whether it is better to learn multiple skills simultaneously (all-at-once) or incrementally (one-...
详细信息
This paper is concerned with the problem of learning multiple skills by modular robots. The main question we address is whether it is better to learn multiple skills simultaneously (all-at-once) or incrementally (one-by- one). We conduct an experimental study with modular robots of various morphologies that need to acquire three different but correlated skills, efficient locomotion, navigation towards a target point, and obstacle avoidance, using a real-time, on-board evolution as the learning method. The results indicate that the one-by-one strategy is more efficient and more stable than the all-at-once strategy.
The author presents robotic engineer Takashi Gomi as a visionary and gives him the credit for introducing Artificial Intelligence( AI) and evolutionary robotics in *** include the author's research work on embodie...
详细信息
The author presents robotic engineer Takashi Gomi as a visionary and gives him the credit for introducing Artificial Intelligence( AI) and evolutionary robotics in *** include the author's research work on embodied AI at Ecole Polytechnique Federale de Lausanne (EPFL) in Switzerland; Khepera, a research robot which could contribute to embodied artificial intelligence; and the concept of soft robots.
This paper presents a behavioral ontogeny for artificial agents based on the interactive memorization of sensorimotor invariants. The agents are controlled by continuous timed recurrent neural networks (CTRNNs) which ...
详细信息
This paper presents a behavioral ontogeny for artificial agents based on the interactive memorization of sensorimotor invariants. The agents are controlled by continuous timed recurrent neural networks (CTRNNs) which bind their sensors and motors within a dynamic system. The behavioral ontogenesis is based on a phylogenetic approach: memorization occurs during the agent's lifetime and an evolutionary algorithm discovers CTRNN parameters. This shows that sensorimotor invariants can be durably modified through interaction with a guiding agent. After this phase has finished, agents are able to adopt new sensorimotor invariants relative to the environment with no further guidance. We obtained these kinds of behaviors for CTRNNs with 3-6 units, and this paper examines the functioning of those CTRNNs. For instance, they are able to internally simulate guidance when it is externally absent, in line with theories of simulation in neuroscience and the enactive field of cognitive science.
Most evolutionary algorithms (EAs) represents a potential solution to a problem as a single-gene chromosome encoding, where the chromosome gives only one output to the problem. However, where more than one output to a...
详细信息
ISBN:
(纸本)9781479944798
Most evolutionary algorithms (EAs) represents a potential solution to a problem as a single-gene chromosome encoding, where the chromosome gives only one output to the problem. However, where more than one output to a problem is required such as in classification and robotic problems, these EAs have to be either modified in order to deal with a multiple output problem or are rendered incapable of dealing with such problems. This paper investigates the parallelisation of genes as independent chromosome entities as described in the Gene Expression Programming (GEP) algorithm. The aim is to investigate the capabilities of a multiple output GEP (moGEP) technique and compare its performance to that of a single-gene GEP chromosome (ugGEP). In the described work, the two GEP approaches are utilised to evolve controllers for a robotic obstacle avoidance and exploration behaviour. The obtained results shows that moGEP is a robust technique for the investigated problem class as well as for utilisation in evolutionary robotics.
暂无评论