Generative representations for the automated design of modular physical robots

  title={Generative representations for the automated design of modular physical robots},
  author={Gregory Hornby and Hod Lipson and Jordan B. Pollack},
  journal={IEEE Trans. Robotics Autom.},
The field of evolutionary robotics has demonstrated the ability to automatically design the morphology and controller of simple physical robots through synthetic evolutionary processes. However, it is not clear if variation-based search processes can attain the complexity of design necessary for practical engineering of robots. Here, we demonstrate an automatic design system that produces complex robots by exploiting the principles of regularity, modularity, hierarchy, and reuse. These… 

Generative Representations for Computer-Automated Evolutionary Design

Generative representations are assembly procedures, or algorithms, for constructing a design thereby allowing for truly novel design solutions to be encoded and by enabling modularity, regularity and hierarchy, the level of sophistication that can be evolved is increased.

Evolution and Morphogenesis of Simulated Modular Robots: A Comparison Between a Direct and Generative Encoding

It is found that the generative encoding is significantly more efficient in creating robot phenotypes in the initial stages of evolution when simulating a maximum of 5, 10, and 20 modules, confirming that generative encodings lead to decent performance more quickly, and that whensimulating just a few modules a generative encode is more powerful than a direct encoding for creating robotic structures.

EDHMoR: Evolutionary designer of heterogeneous modular robots

Evolution and Learning of Virtual Robots

A nature-inspired method that allows virtual robots to modify their morphology through lifetime learning and it is shown that such morphological plasticity makes it possible to evolve robots that can dynamically adjust their morphology to the environment they are placed into.

Designing modular robots

An evolutionary, automated design program is presented that evolves robots in a manner based on genetic programming techniques and tests them in 3D physical simulation against user-specified objectives.

Experiments in design synthesis when behavior is determined by shape

The Erstwhile Agent is built that uses an evolutionary approach to automatically synthesize roBlocks constructions to meet specified desiderata.

Unshackling evolution: evolving soft robots with multiple materials and a powerful generative encoding

The ability of generative soft-voxel systems to scale towards evolving a large diversity of complex, natural, multi-material creatures is suggested.

Computer-Aided Compositional Design and Verification for Modular Robots

A new motion description language (Series-Parallel Action Graphs) is introduced that facilitates the rapid creation of complex behaviors by composition of simpler behaviors and tools to verify configurations and behaviors as they are being created are provided.

Real world morphological evolution is feasible

This work utilizes their shape-shifting quadruped robot, which allows them to optimize the design in its real-world environment, and has seen that the algorithm is able to exploit the dynamic morphology solely through real- world experiments.

Accomplishing high-level tasks with modular robots

An integrated system for addressing high-level tasks with modular robots, extending the original system to include environmentally adaptive parametric behaviors, which integrate motion planners and feedback controllers with the system.



Computer Evolution of Buildable Objects

The work presented takes a step in the problem of body evolution by applying evolutionary techniques to the design of structures assembled out of parts by using a simulator that computes forces and stresses and predicts failure for 2-dimensional Lego structures.

Evolutionary Techniques in Physical Robotics

This work overviews research in four areas: a) High part-count static structures that are buildable, b) The use of commercial CAD/CAM systems as a simulated substrate, c) Dynamic electromechanical systems with complex morphology that can be built automatically, and d) Evolutionary techniques distributed in a physical population of robots.

The advantages of generative grammatical encodings for physical design

  • G. HornbyJ. Pollack
  • Computer Science
    Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546)
  • 2001
This work describes a system for creating generative specifications by combining Lindenmayer systems with evolutionary algorithms, and applies it to the problem of generating table designs and finds that the generative system produces designs with higher fitness and is faster than the non-generative system.

Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines

This book describes the basic concepts and methodologies of evolutionary robotics and the results achieved so far, and describes the clear presentation of a set of empirical experiments of increasing complexity.

Automated learning of muscle-actuated locomotion through control abstraction

We present a learning technique that automatically syn- thesizes realistic locomotion for the animation of physics-based models of animals. The method is especially suitable for animals with highly

Creating High-Level Components with a Generative Representation for Body-Brain Evolution

Applying GENRE to the task of evolving robots for locomotion and comparing it against a non-generative (direct) representation shows that the generative representation system rapidly produces robots with significantly greater fitness.

Automatic design and manufacture of robotic lifeforms

A combined computational and experimental approach is reported in which simple electromechanical systems are evolved through simulations from basic building blocks, and the ‘fittest’ machines are then fabricated robotically using rapid manufacturing technology.

On Modular Design of Field Robotic Systems

The theoretical analysis of the modular design problem for field robots and the application of a hierarchical selection process to solve this problem revealed the large size of the search space.

Evolutionary robotics

The evaluation of a candidate solution necessarily require the evaluation of the behavior that arise by robots that are situated in the external environment and are allowed to ’’live‘‘ long enough to experience a large variety of environmental conditions.

Evolving virtual creatures

A genetic language is presented that uses nodes and connections as its primitive elements to represent directed graphs, which are used to describe both the morphology and the neural circuitry of creatures that move and behave in simulated three-dimensional physical worlds.