Evolution of homing navigation in a real mobile robot

By Dario Floreano, Francesco Mondada. 1996

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

Fitness functions in evolutionary robotics: A survey and analysis (2009, unknown): “The work also used the Khepera robot platform and evolution was conducted using a behavioral fitness function integrand similar to that used in [11]:”
Evolution of Embodied Intelligence (2003, methodology): “To test this hypothesis, at EPFL we put the Khepera robot in an arena with a battery charger in one corner under a light source (figure 2) and let the robot move around as long as its batteries were discharged [9].”
Genetic Representation and Evolvability of Modular Neural Controllers (2010, unknown): “, [6], [7], [8], [9], [10]), swimming robots (e.”
Neuroevolutionary reinforcement learning for generalized control of simulated helicopters (2011, background): “While evolution has also succeeded on-line [58, 71, 77], especially in evolutionary robotics [20, 21, 45, 52, 64, 100], and some research has investigated customizing such methods to on-line settings [14, 15, 21, 65, 83, 89, 90], the problems tackled by evolutionary methods typically assume the avai”
Adaptive Behavior in Competing Co-Evolving Species (2000, background): “, [5]), the robot controller was a simple perceptron of two sigmoid units with recurrent connections at the output layer.”
Evolutionary Computation for Reinforcement Learning (2012, background): “…(Steels, 1994; Nordin and Banzhaf, 1997; Schroder et al, 2001), especially in evolutionary robotics (Meyer et al, 1998; Floreano and Urzelai, 2001; Floreano and Mondada, 2002; Pratihar, 2003; Kernbach et al, 2009; Zufferey et al, 2010), and some research has investigated customizing such methods…”
Evolution of Reinforcement Learning in Uncertain Environments: A Simple Explanation for Complex Foraging Behaviors (2002, background): “In contrast to common evolutionary computation applications involve NNs with evolvable synaptic weights or architectures (e.g., Ackley & Littman, 1991, Floreano & Mondada, 1996, Nolfi, Elman & Parisi, 1994), we set upon the task of evolving the network's neuronal learning rules.”
Towards evolving spiking networks with memristive synapses (2011, background): “Floreano and Mondada [14] present a Discrete Time Recurrent Neural Network (DTRNN) [15] system.”
Evolutionary and Computational Advantages of Neuromodulated Plasticity (2008, background): “Memory units implemented with recurrent connections often provide a behavioural advantage in several tasks like navigation, exploration and foraging (Floreano and Mondada, 1996).”
The evolvability of artificial neural net-works for robot control (2002, background): “The most extensive real world evolution carried out is probably the 10-day evolution of homing navigation (Floreano and Mondada, 1996), however the majority of experiments are carried out in simulation.”
Levels of dynamics and adaptive behavior in evolutionary neural controllers (2002, background): “This information can modulate behavior (Beer and Gallagher, 1992), produce different actions for similar (or lacking) sensory information (Floreano and Mondada, 1996), and be used to detect and represent behavioral sequences (Tani, 1996).”
Embodied Evolution: Distributing an evolutionary algorithm in a population of robots (2002, background): “Keywords:Evolutionary robotics; Artificial Life; Evolutionary algorithms; Distributed learning; Collective robotics”
Robust non-linear control through neuroevolution (2003, background): “Typically, behaviors such as phototaxis or “homing” (Meeden 1998; Ficici et al. 1999; Jakobi et al. 1995; Lund and Hallam 1996; Floreano and Mondada 1996), avoidance of static obstacles (Jakobi et al. 1995; Miglino et al. 1995a; Chavas et al. 22 1998), exploring (Lund and Hallam 1996), or pushing a…”
Autonomous Evolution of Topographic Regularities in Artificial Neural Networks (2010, background): “…exhibit synaptic plasticity (Hubel, Wiesel, & LeVay, 1977), ANNs with plastic synapses have been evolved in the past (Floreano & Urzelai 2000, 2001; Floreano & Mondada, 1996; Risi et al., 2009; Soltoggio et al., 2008), and in principle, HyperNEAT can potentially evolve the geometry of the learning…”
Evolutionary robotics: coping with environmental change (2000, methodology): “Synaptic strength is maintained within a range 0; 1] (notice that a synapse cannot change sign) by adding to the modiication rules a self-limiting component inversely proportional to the synaptic strength itself (Floreano & Mondada, 1996b, 1998, for more details).”