Automatic creation of an autonomous agent: genetic evolution of a neural-network driven robot

By Dario Floreano, Francesco Mondada. 1994

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, background): “Evolutionary Robotics (ER) brought the idea of autonomously designing robots and controllers by means of evolution (Cliff et al., 1993; Floreano and Mondada, 1994, 1996; Urzelai and Floreano, 2000; Floreano and Nolﬁ, 2004).”
On the design of neural networks in the brain by genetic evolution. (2000, methodology): “…range from computer simulated animats (Nol® et al., 1994; Gracias et al., 1996; Huber et al., 1996; Lund and Parisi, 1996) to behavioural robotics (Floreano and Mondada, 1994; Hoshino and Tsuchida, 1996; Kuwana et al., 1996; Husbands et al., 1998), with the genetic algorithm used as a tool to…”
Better Living Through Chemistry: Evolving GasNets for Robot Control (1998, background): “One of the new styles of AI to have emerged recently is Evolutionary Robotics (Cli , Harvey and Husbands, 1993; Nol et al., 1994; Floreano and Mondada, 1994; Yamauchi and Beer, 1994; Husbands and Meyer, 1998).”
Noise and the Reality Gap: The Use of Simulation in Evolutionary Robotics (1995, methodology): “Behaviours developed in simulation did not transfer at all well to the robot, but if the GA run was continued for a few generations in the real world (using techniques similar to those described in [5]) successful robust”
The evolvability of artificial neural net-works for robot control (2002, methodology): “The field of evolutionary robotics applies the techniques of evolutionary computation to the design of robot controllers (Husbands and Harvey, 1992; Brooks, 1992; Cliff et al., 1993; Floreano and Mondada, 1994; Husbands and Meyer, 1998; Nolfi and Floreano, 2000).”
Evolution of homing navigation in a real mobile robot (1996, background): “In fact, unlike the feedforward and internal symmetric structure of the Braitenberg vehicle which cannot drive the robot away from symmetric frontal obstacles, the evolved settings of the recurrent connections are such that our robot never became trapped [23].”
Evolution of Embodied Intelligence (2003, background): “Federal Institute of Technology in Lausanne) [8] and a team at the University of Sussex in Brighton [15] reported the first successful cases where robots evolved with minimal human intervention and developed neural circuits allowing them to autonomously move in real environments.”
Evolving Mobile Robots in Simulated and Real Environments (1995, background): “environment and the same formula to score individuals see [7, 10,17] ( however, in [10] the authors used a simplified version of the formula taking into account only the first 2 terms).”
Genetic and Evolutionary Computation – GECCO 2004 (2004, methodology): “As such, there are similarities between this work and the aggregation mechanisms inherent in Potter and De Jong’s [15][16] cooperative coevolution model and the idea of combining together partial solutions into more complete solutions via sexual recombination (for example, the building-block hypothe”
Evolutionary and Computational Advantages of Neuromodulated Plasticity (2008, background): “The fitness suggested in (Floreano and Mondada, 1994) is the product of three factors: the average wheel speed, a component indicating straight direction and the distance from the walls.”
Embodied Evolution: Distributing an evolutionary algorithm in a population of robots (2002, background): “Keywords:Evolutionary robotics; Artificial Life; Evolutionary algorithms; Distributed learning; Collective robotics”
Evolving developing spiking neural networks (2005, background): “Even if the task is relatively simple, the evolutionary speed is high even when compared to related work [12].”
Evolutionary Robotics and the Radical Envelope-of-Noise Hypothesis (1997, background): “For example, Mataric and Cliff (1996) cite the evolution of collision-free navigation in a Khepera robot, which, in the experiments reported by Floreano and Mondada (1994), took a total of 65 hours (100 generations at 39 minutes per generation) to evolve.1 It is difficult to see how this approach…”