Evolutionary robotics

Last updated

Evolutionary robotics is an embodied approach to Artificial Intelligence (AI) in which robots are automatically designed using Darwinian principles of natural selection. [1] The design of a robot, or a subsystem of a robot such as a neural controller, is optimized against a behavioral goal (e.g. run as fast as possible). Usually, designs are evaluated in simulations as fabricating thousands or millions of designs and testing them in the real world is prohibitively expensive in terms of time, money, and safety.

Contents

An evolutionary robotics experiment starts with a population of randomly generated robot designs. The worst performing designs are discarded and replaced with mutations and/or combinations of the better designs. This evolutionary algorithm continues until a prespecified amount of time elapses or some target performance metric is surpassed.

Evolutionary robotics methods are particularly useful for engineering machines that must operate in environments in which humans have limited intuition (nanoscale, space, etc.). Evolved simulated robots can also be used as scientific tools to generate new hypotheses in biology and cognitive science, and to test old hypothesis that require experiments that have proven difficult or impossible to carry out in reality.

History

In the early 1990s, two separate European groups demonstrated different approaches to the evolution of robot control systems. Dario Floreano and Francesco Mondada at EPFL evolved controllers for the Khepera robot. [2] Adrian Thompson, Nick Jakobi, Dave Cliff, Inman Harvey, and Phil Husbands evolved controllers for a Gantry robot at the University of Sussex. [3] [4] However the body of these robots was presupposed before evolution.

The first simulations of evolved robots were reported by Karl Sims and Jeffrey Ventrella of the MIT Media Lab, also in the early 1990s. [5] [6] However these so-called virtual creatures never left their simulated worlds. The first evolved robots to be built in reality were 3D-printed by Hod Lipson and Jordan Pollack at Brandeis University at the turn of the 21st century. [7]

See also

Related Research Articles

<span class="mw-page-title-main">Genetic algorithm</span> Competitive algorithm for searching a problem space

In computer science and operations research, a genetic algorithm (GA) is a metaheuristic inspired by the process of natural selection that belongs to the larger class of evolutionary algorithms (EA). Genetic algorithms are commonly used to generate high-quality solutions to optimization and search problems via biologically inspired operators such as selection, crossover, and mutation. Some examples of GA applications include optimizing decision trees for better performance, solving sudoku puzzles, hyperparameter optimization, and causal inference.

<span class="mw-page-title-main">Evolutionary computation</span> Trial and error problem solvers with a metaheuristic or stochastic optimization character

In computer science, evolutionary computation is a family of algorithms for global optimization inspired by biological evolution, and the subfield of artificial intelligence and soft computing studying these algorithms. In technical terms, they are a family of population-based trial and error problem solvers with a metaheuristic or stochastic optimization character.

NeuroEvolution of Augmenting Topologies (NEAT) is a genetic algorithm (GA) for the generation of evolving artificial neural networks developed by Kenneth Stanley and Risto Miikkulainen in 2002 while at The University of Texas at Austin. It alters both the weighting parameters and structures of networks, attempting to find a balance between the fitness of evolved solutions and their diversity. It is based on applying three key techniques: tracking genes with history markers to allow crossover among topologies, applying speciation to preserve innovations, and developing topologies incrementally from simple initial structures ("complexifying").

Neuroevolution, or neuro-evolution, is a form of artificial intelligence that uses evolutionary algorithms to generate artificial neural networks (ANN), parameters, and rules. It is most commonly applied in artificial life, general game playing and evolutionary robotics. The main benefit is that neuroevolution can be applied more widely than supervised learning algorithms, which require a syllabus of correct input-output pairs. In contrast, neuroevolution requires only a measure of a network's performance at a task. For example, the outcome of a game can be easily measured without providing labeled examples of desired strategies. Neuroevolution is commonly used as part of the reinforcement learning paradigm, and it can be contrasted with conventional deep learning techniques that use backpropagation with a fixed topology.

Evolvable hardware (EH) is a field focusing on the use of evolutionary algorithms (EA) to create specialized electronics without manual engineering. It brings together reconfigurable hardware, evolutionary computation, fault tolerance and autonomous systems. Evolvable hardware refers to hardware that can change its architecture and behavior dynamically and autonomously by interacting with its environment.

<span class="mw-page-title-main">S-bot mobile robot</span>

The s-bot is a small (15 cm) differential wheeled mobile robot developed at the LIS at the EPFL in Lausanne, Switzerland between 2001 and 2004. Targeted to swarm robotics, a field of artificial intelligence, it was developed within the Swarm-bots project, a Future and Emerging Technologies project coordinated by Prof. Marco Dorigo. Built by a small team of engineers of the group of Prof. Dario Floreano and with the help of student projects, it is considered at the time of completion as one of the most complex and featured robots ever for its size. The s-bot was ranked on position 39 in the list of “The 50 Best Robots Ever” by the Wired magazine in 2006.

<span class="mw-page-title-main">Dario Floreano</span> Swiss-Italian roboticist and engineer

Dario Floreano is a Swiss-Italian roboticist and engineer. He is Director of the Laboratory of Intelligent System (LIS) at the École Polytechnique Fédérale de Lausanne in Switzerland and was the founding director of the Swiss National Centre of Competence in Research (NCCR) Robotics.

Inman Harvey is a former senior lecturer in computer science and artificial intelligence at the University of Sussex; he is now a visiting senior research fellow at the same university. His research interests largely centre on the development of artificial evolution as an approach to the design of complex systems. Application domains of interest include evolutionary robotics, evolvable hardware, molecules for pharmaceutical purposes.

Phil Husbands is a professor of computer science and artificial intelligence at the English University of Sussex, situated next to the East Sussex village of Falmer, within the city of Brighton and Hove. He is head of the Evolutionary and Adaptive Systems group and co-director of the Centre for Computational Neuroscience and Robotics (CCNR). Husbands is also one of the founders of the field of evolutionary robotics.

Stefano Nolfi is a director of research of the Institute of Cognitive Sciences and Technologies at the Consiglio Nazionale delle Ricerche and head of the Laboratory of Autonomous Robots and Artificial Life. He is one of the founders of Evolutionary robotics. Nolfi's research interests include: evolution of communication and language, language and action, adaptive behavior, swarm robotics.

Robotics is the branch of technology that deals with the design, construction, operation, structural disposition, manufacture and application of robots. Robotics is related to the sciences of electronics, engineering, mechanics, and software. The word "robot" was introduced to the public by Czech writer Karel Čapek in his play R.U.R., published in 1920. The term "robotics" was coined by Isaac Asimov in his 1941 science fiction short-story "Liar!"

Neurorobotics is the combined study of neuroscience, robotics, and artificial intelligence. It is the science and technology of embodied autonomous neural systems. Neural systems include brain-inspired algorithms, computational models of biological neural networks and actual biological systems. Such neural systems can be embodied in machines with mechanic or any other forms of physical actuation. This includes robots, prosthetic or wearable systems but also, at smaller scale, micro-machines and, at the larger scales, furniture and infrastructures.

Artificial development, also known as artificial embryogeny or machine intelligence or computational development, is an area of computer science and engineering concerned with computational models motivated by genotype–phenotype mappings in biological systems. Artificial development is often considered a sub-field of evolutionary computation, although the principles of artificial development have also been used within stand-alone computational models.

<span class="mw-page-title-main">HyperNEAT</span>

Hypercube-based NEAT, or HyperNEAT, is a generative encoding that evolves artificial neural networks (ANNs) with the principles of the widely used NeuroEvolution of Augmented Topologies (NEAT) algorithm developed by Kenneth Stanley. It is a novel technique for evolving large-scale neural networks using the geometric regularities of the task domain. It uses Compositional Pattern Producing Networks (CPPNs), which are used to generate the images for Picbreeder.orgArchived 2011-07-25 at the Wayback Machine and shapes for EndlessForms.comArchived 2018-11-14 at the Wayback Machine. HyperNEAT has recently been extended to also evolve plastic ANNs and to evolve the location of every neuron in the network.

Morphogenetic robotics generally refers to the methodologies that address challenges in robotics inspired by biological morphogenesis.

Evolutionary developmental robotics refers to methodologies that systematically integrate evolutionary robotics, epigenetic robotics and morphogenetic robotics to study the evolution, physical and mental development and learning of natural intelligent systems in robotic systems. The field was formally suggested and fully discussed in a published paper and further discussed in a published dialogue.

<span class="mw-page-title-main">Dave Cliff (computer scientist)</span>

David T. Cliff is a Professor in the Department of Computer Science at the University of Bristol and was formerly the Director of the UK Large-scale Complex IT Systems (LSCITS) Initiative. Cliff is the inventor of the seminal "ZIP" trading algorithm, one of the first of the current generation of autonomous adaptive algorithmic trading systems, which was demonstrated to outperform human traders in research published in 2001 by IBM. He is also the inventor on multiple international patents from the early 2000s concerning his invention hpDJ, the world's first fully automated disk-jockey (DJ) system for electronic dance music, the precursor to present-day DJ automation tools such as Traktor.

Jordan B. Pollack is a professor of computer science at Brandeis University, and director of the Dynamical and Evolutionary Machine Organization lab. Pollack's work with David Waltz was highly acclaimed by Marvin Minsky. His contributions to theoretical computer science include the demonstration of a neural network implementation of a Turing machine, the Neuring machine, in 1987. Pollack and Hod Lipson pioneered the automated design and manufacturing of robots. In January 2001 he was named one of MIT Technology Review's "TR 10".

<span class="mw-page-title-main">Sabine Hauert</span> Roboticist

Sabine Hauert is Professor of Swarm Engineering in the Bristol Robotics Laboratory at the University of Bristol where her research investigates swarm robotics. Previously she worked at the Massachusetts Institute of Technology (MIT), Carnegie Mellon University (CMU) and the École Polytechnique Fédérale de Lausanne (EPFL) in Switzerland.

<span class="mw-page-title-main">Pavan Ramdya</span> US-American neuroscientist

Pavan Ramdya is an American and Swiss neuroscientist and bioengineer. His research centers on understanding the cognitive and neuromechanical control of behavior toward applications in robotics and artificial intelligence. He holds the Firmenich Next Generation Chair in neuroscience and bioengineering at EPFL, and is head of the Neuroengineering Laboratory at EPFL's School of Life Sciences.

References

  1. ↑ Bongard, Josh (2013). "Evolutionary Robotics". Communications of the ACM. 56 (8): 74–83. doi: 10.1145/2493883 . S2CID   16097970.
  2. ↑ Floreano, Dario; Mondada, Francesco (1996). "Evolution of homing navigation in a real mobile robot" (PDF). IEEE Transactions on Systems, Man, and Cybernetics. 26 (3): 396–407. doi:10.1109/3477.499791. PMID   18263042.
  3. ↑ Cliff, Dave; Husbands, Phil; Harvey, Inman (1993). "Explorations in Evolutionary Robotics". Adaptive Behavior. 2 (1): 73–110. doi:10.1177/105971239300200104. S2CID   2979661.
  4. ↑ Harvey, Inman; Husbands, Phil; Cliff, Dave; Thompson, Adrian; Jakobi, Nick (1997). "Evolutionary robotics: the Sussex approach". Robotics and Autonomous Systems. 20 (2–4): 205–224. doi:10.1016/S0921-8890(96)00067-X.
  5. ↑ Sims, Karl (1994). "Evolving 3D morphology and behavior by competition". Artificial Life. 1 (4): 353–372. doi:10.1162/artl.1994.1.4.353. S2CID   3261121.
  6. ↑ Ventrella, Jeffrey (1994). Explorations in the emergence of morphology and locomotion behavior in animated characters. Artificial life. pp. 436–441.
  7. ↑ Lipson, Hod; Pollack, Jordan (2000). "Automatic design and manufacture of robotic lifeforms". Nature. 406 (6799): 974–978. Bibcode:2000Natur.406..974L. doi:10.1038/35023115. PMID   10984047. S2CID   4317402.
This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.