Automatic design and manufacture of robotic lifeforms

By Hod Lipson, Jordan B. Pollack. Nature, 2000

853 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Astronomy and Astrophysics, Mechanical Engineering

View Paper: https://www.semanticscholar.org/paper/03088fa9fd56c439826f408a276266cc49886be8

How researchers see this paper

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

In Artificial Intelligence

In Astronomy and Astrophysics

In Mechanical Engineering

Citations in the corpus

Competitive Coevolution through Evolutionary Complexification (2011, background): “200a,b), genetic programs (Koza 1992), robot body morphologies (Lipson and Pollack 2000), Bayesian networks (Mengshoel 1999), finite automata (Brave 1996), and building and vehicle architectures (O’Reilly 2000) are all structures of varying complexity that can benefit from complexification.”
Embodied intelligence via learning and evolution (2021, background): “…scaling of computation and models that has been so successful in other ﬁelds of AI 6,18–20 and bring it bear on the ﬁeld of evolutionary robotics 21 ; (2) the introduction of a UNIMAL, a UNIversal aniMAL morphological design space that is both highly expressive yet also enriched for useful…”
Unshackling evolution: evolving soft robots with multiple materials and a powerful generative encoding (2013, background): “(right) The scale and resolution of robot fabrication techniques (from Lipson and Pollack, 2000 [22]). produce more natural, complex forms if it is able to create organisms out of many material types.”
Six Human-Centered Artificial Intelligence Grand Challenges (2023, neutral): “Another approach uses Darwinian evolution algorithms (AI) to create neural networks algorithms (AI) that become progressively good at solving problems (Lipson & Pollack, 2000).”
Creating Brain-Like Intelligence (2009, background): “Note, that this goes beyond the co-evolution of body and brain that has been demonstrated by Lipson and Pollack [ 31 ].”
Quality and Diversity Optimization: A Unifying Modular Framework (2017, methodology): “For example, evolutionary methods have been used to optimize the morphologies and the neural networks of physical robots [7], and to infer the equations behind collected data [8].”
A scalable pipeline for designing reconfigurable organisms (2020, background): “Moreover, they are agnostic to the kind of artifact being designed and the function it should provide: the same evolutionary algorithm can be reconfigured to design drugs (15), autonomous machines (11, 13), metamaterials (16), or architecture (17).”
Fitness functions in evolutionary robotics: A survey and analysis (2009, positive): “One of the major achievements of the field of ER as a whole is that it has demonstrated that sophisticated evolvable robot control structures (such as neural networks) can be trained to produce functional behaviors in real (embodied) autonomous robots.”
Picbreeder: A Case Study in Collaborative Evolutionary Exploration of Design Space (2011, background): “As the popularity of personal rapid prototyping machines increases (Lipson and Pollack, 2000; Malone and Lipson, 2007), Picbreeder-like systems may evolve threedimensional objects that can be downloaded and automatically built.”