How to Evolve Autonomous Robots: Different Approaches in Evolutionary Robotics

By Stefano Nolfi, Dario Floreano, O. Miglino, 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

Deep learning in neural networks: An overview (2014, background): “Many RNN evolvers have been proposed (e.g., Miller et al., 1989; Wieland, 1991; Cliff et al., 1993; Yao, 1993; Nolfi et al., 1994a; Sims, 1994; Yamauchi and Beer, 1994; Miglino et al., 1995; Moriarty, 1997; Pasemann et al., 1999; Juang, 2004).”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, methodology): “1, except that C is now an FNN or RNN trained by evolutionary algorithms [200, 255, 105, 56, 68] applied to NNs [165, 321, 180, 259, 72, 90, 89, 110, 94], or by policy gradient methods [314, 315, 316, 274, 18, 1, 63, 128, 313, 210, 192, 191, 256, 85, 312, 190, 82, 93][245, Sec.”
The Transferability Approach: Crossing the Reality Gap in Evolutionary Robotics (2013, unknown): “Nolﬁ et al. reported a similar work regarding a navigation task addressed by a mobile Khepera robot with 30000 evaluations in simulation followed by 3000 evaluations on the physical robot [47].”
Noise and the Reality Gap: The Use of Simulation in Evolutionary Robotics (1995, methodology): “The simulation is based on a spatially continuous, two dimensional model of the underlying real world physics and not on a look-up tabl approach as in [15].”
Evolutionary Robotics and the Radical Envelope-of-Noise Hypothesis (1997, background): “…testing procedure is far from a trivial matter and [with the exception of certain hybrid approaches (Thompson, 1995; Nolfi, Floreano, Miglino, & Mondada, 1994a)] can be done in only one of two ways: Control architectures either must be evaluated on real robots in the real world, or they must…”
Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes (2008, unknown): “Many approaches to evolving RNNs have been proposed [34, 111, 110, 37 , 33, 93, 35, 15].”
Training Recurrent Networks by Evolino (2007, background): “more efficient and principled way is to search the space of RNN weight matrices [20,21,26,45,53,54] using evolutionary algorithms [13,31,41].”
Evolution of homing navigation in a real mobile robot (1996, methodology): “Thus, although one may obtain comparable results in simpli ed environments and well de ned tasks [16], it has not yet been shown that the same holds for more complex situations.”
Self-Organized Coordinated Motion in Groups of Physically Connected Robots (2007, background): “The sensor is composed of two portions: one connected to the turret and the other one to the chassis (see Fig.”
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).”
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).”