Active Guidance for a Finless Rocket Using Neuroevolution

By Faustino J. Gomez, Risto Miikkulainen. 2003

133 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Deep learning in neural networks: An overview (2014, background): “One particularly effective family of methods coevolves neurons, combining them into networks, and selecting those neurons for reproduction that participated in the best-performing networks (Moriarty and Miikkulainen, 1996; Gomez, 2003; Gomez and Miikkulainen, 2003).”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, methodology): “1 RL through Direct and Indirect Search in RNN Program Space It is possible to train small RNNs with a few 100 or 1000 weights using evolutionary algorithms [200, 255, 105, 56, 68] to search the space of NN weights [165, 307, 44, 321, 180, 259, 320, 164, 173, 69, 71, 187, 121, 313, 66, 270, 269, 305”
One Big Net For Everything (2018, background): “Without a teacher, reward-maximizing programs of an RNN must be learned through repeated trial and error, e.g., through artiﬁcial evolution [39, 107, 83, 40, 16, 18, 103, 14, 89, 88] [76, Sec.”
A System for Robotic Heart Surgery that Learns to Tie Knots Using Recurrent Neural Networks (2006, methodology): “The particular instantiation of Evolino in this paper uses the Enforced SubPopulations algorithm (ESP; [18], [19]) to evolve LSTM networks.”
Evolving Soccer Keepaway Players Through Task Decomposition (2005, methodology): “In these benchmark sequential decision tasks, ESP was shown to outperform other neuroevolution algorithms as well as several reinforcement learning methods ( Gomez & Miikkulainen, 1997, 1999, 2001, 2003 ).”
Neuroevolution (2010, background): “For instance, neural network controllers have been evolved to drive mobile robots, automobiles, and even rockets [6, 14, 19].”
Neural Modularity Helps Organisms Evolve to Learn New Skills without Forgetting Old Skills (2015, background): “These algorithms have shown impressive performance—often outperforming human engineers [40, 41]—on a range of tasks, such as measuring properties in quantum physics [12], dynamic rocket guidance [42], and robot locomotion [43, 44].”
Evolino for recurrent support vector machines (2005, methodology): “For continuous function generation, backprojection (or teacher forcing in standard RNN terminology) is used, where the predicted outputs are fed back as inputs in the next time step, such that 1 becomes: φ(t) = f(W,u(t), y(t−1),u(t−1), . . . , y(0),u(0)).”
Evolutionary Bilevel Optimization for Complex Control Tasks (2015, background): “EAs have been demonstrated to perform well in many complex control problems, such as finless rocket stabilization, race-car driving, bipedal walking, and helicopter hovering [12, 13, 14, 15].”
Genetic Representation and Evolvability of Modular Neural Controllers (2010, methodology): “In this paper, we identify interference between the adaptation of different parts of the control system as one of the key challenges in the evolutionary synthesis of artificial neural networks.”
Accelerated Neural Evolution through Cooperatively Coevolved Synapses (2008, background): “, 2001; Grasemann and Miikkulainen, 2005), including the real world reinforcement learning task of finless rocket control (Gomez and Miikkulainen, 2003).”
Evolutionary Computation for Reinforcement Learning (2012, background): “ESP has even been used to evolve control systems for a finless sounding rocket (Gomez and Miikkulainen, 2003).”