This paper addresses the problem of designing behavioural strategies for a group of robots with a specific task, capturing another robot. Our proposed approach is to employ a "smart" prey with a pre-programm...
详细信息
ISBN:
(纸本)9781728124858
This paper addresses the problem of designing behavioural strategies for a group of robots with a specific task, capturing another robot. Our proposed approach is to employ a "smart" prey with a pre-programmed strategy based on a novel Gaussian model of danger zones and use an evolutionary algorithm (EA) to optimize the predators' behavior. The EA is applied in two stages: first in simulation, then in hardware on the real robots. The best evolved robot controllers are then further inspected and compared by their robustness, i.e., performance under different conditions. The results show that our approach is successful, combining simulations, real-world evolution, and robustness analysis it is possible to develop good solutions for the predator-prey problem.
Distributed Embodied Evolution (dEE) is a powerful approach to learn behaviors in robot swarms by exploiting their intrinsic parallelism: each robot runs an evolutionary algorithm, and locally shares its learning expe...
详细信息
ISBN:
(数字)9783030166922
ISBN:
(纸本)9783030166915;9783030166922
Distributed Embodied Evolution (dEE) is a powerful approach to learn behaviors in robot swarms by exploiting their intrinsic parallelism: each robot runs an evolutionary algorithm, and locally shares its learning experience with other nearby robots. Given the distributed nature of this approach, dEE entails different evolutionary dynamics when compared to standard centralized evolutionary robotics. In this paper, we investigate the distributed evolution of Gene Regulatory Networks (GRNs) as controller representation to learn swarm robot behavior, which have been extensively used for the evolution of single-robot behavior with remarkable success. Concretely, we use dEE to evolve fixed-topology GRN swarm robot controllers for an item collection task;this constitutes the first work to evolve GRNs in distributed swarm robot settings. To improve our understanding of such distributed GRN evolution, we analyze the fitness and the behavioral diversity of the swarm over generations when using 5 levels of increasing local selection pressure and 4 different swarm sizes, from 25 to 200 robots. Our experiments reveal that there exist different regimes, depending on the swarm size, in the relationship between local selection pressure, and both behavioral diversity and overall swarm performance, providing several insights on distributed evolution. We further use a metric to quantify selection pressure in evolutionary systems, which is based on the correlation between number of offspring and fitness of the behaviors. This reveals a complex relationship on the overall selection pressure between the ability or ease to spread genomes (or environmental pressure), and the fitness of the behavior (or task-oriented (local) pressure), opening new research questions. We conclude the paper by discussing the need for developing specialized statistical tools to facilitate the analysis of the large and diverse amount of data relevant to distributed Embodied Evolution.
We study on artificial neural network-based controllers which are either trained or evolved by using the supervised or unsupervised learning approach. We employed backpropagation for the supervised method and the gene...
详细信息
ISBN:
(纸本)9780769542539
We study on artificial neural network-based controllers which are either trained or evolved by using the supervised or unsupervised learning approach. We employed backpropagation for the supervised method and the genetic algorithm for the unsupervised method. After training the controllers, we applied the controllers to our three newly designed mini-3D games. We performed a comprehensive study on the performance and weaknesses of the controllers. We emerged the controllers as fundamental tools for giving us more understanding about artificial neural network and its effectiveness in imitating players' behaviours.
One of the factors that affect the success of evolutionary robotics (ER) is the way fitness functions are designed to operate. While needs-based custom fitness functions have been developed, most of the time they have...
详细信息
ISBN:
(纸本)9781538644447
One of the factors that affect the success of evolutionary robotics (ER) is the way fitness functions are designed to operate. While needs-based custom fitness functions have been developed, most of the time they have been defined in simpler mathematical functions to reduce the computation time. In this paper, we hypothesize that an incremental fitness function based on established techniques in specific task domains in robotics will aid the evolution process. An A-star algorithm-based fitness function for path planning is designed and implemented for evolving the body plans and controllers of robots for navigation and obstacle avoidance tasks. It has been shown that using this concept, fitter robots have evolved in most cases when compared to simple distance-only based fitness functions. However, due to variable performance of the evolver with the A-star fitness function, the results are inconclusive. We also identify problems associated with the fitness function and make recommendations for designing future fitness functions based on observations of the experiments.
It is a difficult task to generate optimal walking gaits for mobile legged robots. Generating and coordinating an optimal gait involves continually repeating a series of actions in order to create a sustained movement...
详细信息
ISBN:
(纸本)9781457706530
It is a difficult task to generate optimal walking gaits for mobile legged robots. Generating and coordinating an optimal gait involves continually repeating a series of actions in order to create a sustained movement. In this work, we present the use of a Cyclic Genetic Algorithm (CGA) to learn near optimal gaits for an actual quadruped servo-robot with three degrees of movement per leg. This robot was used to create a simulation model of the movement and states of the robot which included the robot's unique features and capabilities. The CGA used this model to learn gaits that were optimized for this particular robot. Tests done in simulation show the success of the CGA in evolving gait control programs and tests on robot show that these control programs produce reasonable gaits.
Anytime Learning with Fitness Biasing has been shown in previous works to be an effective tool for evolving hexapod gaits. In this paper, we present the use of Anytime Learning with Fitness Biasing to evolve the contr...
详细信息
ISBN:
(纸本)9781457706530
Anytime Learning with Fitness Biasing has been shown in previous works to be an effective tool for evolving hexapod gaits. In this paper, we present the use of Anytime Learning with Fitness Biasing to evolve the controller for a robot learning the box pushing task. The robot that was built for this task, was measured to create an accurate model. The model was used in simulation to test the effectiveness of Anytime Learning with Fitness Biasing for the box pushing task. This work is the first step in new research where an automated system to test the viability of Fitness Biasing will be created, as well as the first application of Fitness Biasing to a high level task such as box pushing.
While evolving evolutionary robotics controllers for real vehicles is an active area of research, most research robots do not require any assurance prior to operation that an evolved controller will not damage the veh...
详细信息
ISBN:
(纸本)9781595931863
While evolving evolutionary robotics controllers for real vehicles is an active area of research, most research robots do not require any assurance prior to operation that an evolved controller will not damage the vehicle. For controllers evolved in simulation where testing a poorly performing controller might damage the vehicle, thorough testing in simulation-subject to multiple sources of sensor and state noise is required. Evolved controllers must be robust to noise in the environment in order to operate the vehicle safely. We have evolved navigation controllers for unmanned aerial vehicles in simulation using multi-objective genetic programming, and in order to choose the best evolved controller and to assure that this controller will perform well under a variety of environmental conditions, we have performed a series of robustness tests. The results show that our best evolved controller outperforms two hand-designed controllers and is robust to many sources of noise.
To investigate how encodings influence evolving the morphology and control of modular robots, we compared three encodings: a direct encoding and two generative encodings a compositional pattern producing network (CPPN...
详细信息
ISBN:
(纸本)9781450367486
To investigate how encodings influence evolving the morphology and control of modular robots, we compared three encodings: a direct encoding and two generative encodings a compositional pattern producing network (CPPN) and a Lindenmayer System (L-System). The evolutionary progression and final performance of the direct encoding and the L-System was significantly better than the CPPN. The generative encodings converge quicker than the direct encoding in terms of morphological and controller diversity.
The Voxbot is a cubic (voxel) shaped robot actuated by expansion and contraction of its 12 edges designed for running evolutionary experiments, built as cheaply as possible. Each edge was made of a single 10ml medical...
详细信息
ISBN:
(纸本)9783319088648;9783319088631
The Voxbot is a cubic (voxel) shaped robot actuated by expansion and contraction of its 12 edges designed for running evolutionary experiments, built as cheaply as possible. Each edge was made of a single 10ml medical syringe for pneumatic control. These were connected to an array of 12 servos situated on an external housing and controlled with an Arduino microcontroller from a laptop. With twenty motor primitive commands and the slow response of its pneumatics this robot allows real time controllers to be evolved in situ rather than just in simulation. With simple combinations and sequencing of motor primitives the Voxbot can be made to walk, rotate and crab crawl. The device is available in kit form and is very easy to build and replicate. Other morphologies can be built easily.
Creating robust robot platforms that function in the real world is a difficult task. Adding the requirement that the platform should be capable of learning, from nothing, ways to generate its own movement makes the ta...
详细信息
ISBN:
(纸本)9783030356644;9783030356637
Creating robust robot platforms that function in the real world is a difficult task. Adding the requirement that the platform should be capable of learning, from nothing, ways to generate its own movement makes the task even harder. evolutionary robotics is a promising field that combines the creativity of evolutionary optimization with the real-world focus of robotics to bring about unexpected control mechanisms in addition to whole new robot designs. Constructing a platform that is capable of these feats is difficult, and it is important to share experiences and lessons learned so that designers of future robot platforms can benefit. In this paper, we introduce our robotics platform and detail our experiences with real-world evolution. We present thoughts on initial design considerations and key insights we have learned from extensive experimentation. We hope to inspire new platform development and hopefully reduce the threshold of doing real-world legged robot evolution.
暂无评论