Content uploaded by Kyrre Glette
Author content
All content in this area was uploaded by Kyrre Glette on Jun 02, 2015
Content may be subject to copyright.
A preview of the PDF is not available
Real-World Reproduction of Evolved Robot Morphologies: Automated Categorization and Evaluation
Abstract and Figures
This paper describes the real-world reproduction of a handful of robots selected from a larger sample of simulated models previously generated by an evolutionary algorithm. The five robots, which are selected by automatic clustering to be representative of different morphological niches present in the sample, are constructed in the real world using off-the-shelf motor components, combined with 3D printed structural parts that were automatically generated based on the simulator models. A lab setup, involving evolution of turning gaits for each robot, is used to automate the experiments. The forward walking speeds of the constructed robots are measured, and compared with the simulated speeds. While some of the robots achieve near-identical results, some show a large performance loss compared to their simulated prototypes, underlining the reality gap issue seen in similar previous works.
Figures - uploaded by Kyrre Glette
Author content
All figure content in this area was uploaded by Kyrre Glette
Content may be subject to copyright.
... They used 3D printing to manufacture the mechanical parts and manually assembled the motors and wires. Similarly, Samuelsen and Glette (2015); Auerbach et al. (2014); Vujovic et al. (2017); Buchanan et al. (2020) also used 3D printing for manufacturing evolved robots. ...
... Some of the real robots transferred were close to the limits of the space that the camera was able to track (around 2 × 1 m) and the workspace for small manipulators is even less (0.5 × 1 m with an UR5). Other works have solved this problem by making the robot automatically return in case of reaching the limits of the space (Samuelsen and Glette, 2015), pulling cables tied to the robot or resetting the position of the robots manually. However, none of these systems can easily be applied to automatic systems in which the morphology changes. ...
This work presents a platform for evolution of morphology in full cycle reconfigurable hardware: The EMERGE (Easy Modular Embodied Robot Generator) modular robot platform. Three parts necessary to implement a full cycle process, i.e., assembling the modules in morphologies, testing the morphologies, disassembling modules and repeating, are described as a previous step to testing a fully autonomous system: the mechanical design of the EMERGE module, extensive tests of the modules by first assembling them manually, and automatic assembly and disassembly tests. EMERGE modules are designed to be easy and fast to build, one module is built in half an hour and is constructed from off-the-shelf and 3D printed parts. Thanks to magnetic connectors, modules are quickly attached and detached to assemble and reconfigure robot morphologies. To test the performance of real EMERGE modules, 30 different morphologies are evolved in simulation, transferred to reality, and tested 10 times. Manual assembly of these morphologies is aided by a visual guiding tool that uses AprilTag markers to check the real modules positions in the morphology against their simulated counterparts and provides a color feedback. Assembly time takes under 5 min for robots with fewer than 10 modules and increases linearly with the number of modules in the morphology. Tests show that real EMERGE morphologies can reproduce the performance of their simulated counterparts, considering the reality gap. Results also show that magnetic connectors allow modules to disconnect in case of being subjected to high external torques that could damage them otherwise. Module tracking combined with their easy assembly and disassembly feature enable EMERGE modules to be also reconfigured using an external robotic manipulator. Experiments demonstrate that it is possible to attach and detach modules from a morphology, as well as release the module from the manipulator using a passive magnetic gripper. This shows that running a completely autonomous, evolution of morphology in full cycle reconfigurable hardware of different topologies for robots is possible and on the verge of being realized. We discuss EMERGE features and the trade-off between reusability and morphological variability among different approaches to physically implement evolved robots.
... The Autonomous Robot Evolution (ARE) project 1 sought to achieve this with an autonomous fabrication system, using a combination of 3D printing and modular functional parts to enable a wide range of evolved body plans to be rapidly implemented in hardware. This semi-modular approach is distinct from the discrete modular approach, whereby robots are constructed entirely from prefabricated modules (Brodbeck et al., 2015;Miras et al., 2020;Moreno and Faiña, 2021), and little research has been carried out with hardware robots that can take more arbitrary shapes (Samuelsen and Glette, 2015;Kriegman et al., 2020b). ...
The evolutionary robotics field offers the possibility of autonomously generating robots that are adapted to desired tasks by iteratively optimising across successive generations of robots with varying configurations until a high-performing candidate is found. The prohibitive time and cost of actually building this many robots means that most evolutionary robotics work is conducted in simulation, but to apply evolved robots to real-world problems, they must be implemented in hardware, which brings new challenges. This paper explores in detail the design of an example system for realising diverse evolved robot bodies, and specifically how this interacts with the evolutionary process. We discover that every aspect of the hardware implementation introduces constraints that change the evolutionary space, and exploring this interplay between hardware constraints and evolution is the key contribution of this paper. In simulation, any robot that can be defined by a suitable genetic representation can be implemented and evaluated, but in hardware, real-world limitations like manufacturing/assembly constraints and electrical power delivery mean that many of these robots cannot be built, or will malfunction in operation. This presents the novel challenge of how to constrain an evolutionary process within the space of evolvable phenotypes to only those regions that are practically feasible: the viable phenotype space. Methods of phenotype filtering and repair were introduced to address this, and found to degrade the diversity of the robot population and impede traversal of the exploration space. Furthermore, the degrees of freedom permitted by the hardware constraints were found to be poorly matched to the types of morphological variation that would be the most useful in the target environment. Consequently, the ability of the evolutionary process to generate robots with effective adaptations was greatly reduced. The conclusions from this are twofold. 1) Designing a hardware platform for evolving robots requires different thinking, in which all design decisions should be made with reference to their impact on the viable phenotype space. 2) It is insufficient to just evolve robots in simulation without detailed consideration of how they will be implemented in hardware, because the hardware constraints have a profound impact on the evolutionary space.
... The dominant approaches are using Central Pattern Generators (CPGs) 23 . Most papers studied gait learning with real robots using an open-loop controller with no sensory feedback from the environment 24,25,26,27 . For closed-loop controllers, joint angle and foot contact are typically used to be the sensory feedback. ...
The challenge of robotic reproduction -- making of new robots by recombining two existing ones -- has been recently cracked and physically evolving robot systems have come within reach. Here we address the next big hurdle: producing an adequate brain for a newborn robot. In particular, we address the task of targeted locomotion which is arguably a fundamental skill in any practical implementation. We introduce a controller architecture and a generic learning method to allow a modular robot with an arbitrary shape to learn to walk towards a target and follow this target if it moves. Our approach is validated on three robots, a spider, a gecko, and their offspring, in three real-world scenarios.
... Although QD algorithms have been applied to the evolution of artificial creatures [26] and morphological descriptors have been used to evolve modular robots [6], [27] few examples exist applying the QD paradigm to modular robotics. This makes our contribution valuable, opening up a new application area for QD and introducing a way to generate a repertoire of possible morphologies within modular robotics that can later be experimented on in the real world. ...
In Evolutionary Robotics a population of solutions is evolved to optimize robots that solve a given task. However, in traditional Evolutionary Algorithms, the population of solutions tends to converge to local optima when the problem is complex or the search space is large, a problem known as premature convergence. Quality Diversity algorithms try to overcome premature convergence by introducing additional measures that reward solutions for being different while not necessarily performing better. In this paper we compare a single objective Evolutionary Algorithm with two diversity promoting search algorithms; a Multi-Objective Evolutionary Algorithm and MAP-Elites a Quality Diversity algorithm, for the difficult problem of evolving control and morphology in modular robotics. We compare their ability to produce high performing solutions, in addition to analyze the evolved morphological diversity. The results show that all three search algorithms are capable of evolving high performing individuals. However, the Quality Diversity algorithm is better adept at filling all niches with high-performing solutions. This confirms that Quality Diversity algorithms are well suited for evolving modular robots and can be an important means of generating repertoires of high performing solutions that can be exploited both at design- and runtime.
In modular robotics modules can be reconfigured to change the morphology of the robot, making it able to adapt to specific tasks. However, optimizing both the body and control of such robots is a difficult challenge due to the intricate relationship between fine-tuning control and morphological changes that can invalidate such optimizations. These challenges can trap many optimization algorithms in local optima, halting progress towards better solutions. To solve this challenge we compare three different Evolutionary Algorithms on their capacity to optimize high performing and diverse morphologies and controllers in modular robotics. We compare two objective-based search algorithms, with and without a diversity promoting objective, with a Quality Diversity algorithm—MAP-Elites. The results show that MAP-Elites is capable of evolving the highest performing solutions in addition to generating the largest morphological diversity. Further, MAP-Elites is superior at regaining performance when transferring the population to new and more difficult environments. By analyzing genealogical ancestry we show that MAP-Elites produces more diverse and higher performing stepping stones than the two other objective-based search algorithms. The experiments transitioning the populations to new environments show the utility of morphological diversity, while the analysis of stepping stones show a strong correlation between diversity of ancestry and maximum performance on the locomotion task. Together, these results demonstrate the suitability of MAP-elites for the challenging task of morphology-control search for modular robots, and shed light on the algorithm’s capability of generating stepping stones for reaching high-performing solutions.
The challenge of robotic reproduction {making of new robots by recombiningtwo existing ones{ has been recently cracked and physically evolving robot systems have come within reach. Here we address the next big hurdle: producing an adequate brain for a newborn robot. In particular, we address the task of targeted locomotion which is arguably a fundamental skill in any practical implementation. We introduce a controller architecture and a generic learning method to allow a modular robot with an arbitrary shape to learn to walk to wards a target and follow this target if it moves. Our approach is validated on three robots, a spider, a gecko, and their offspring, in three real-world scenarios.
In modular robotics, modules can be reconfigured to change the morphology of the robot, making it able to adapt for specific tasks. However, optimizing both the body and control is a difficult challenge due to the intricate relationship between fine-tuning control and morphological changes that can invalidate such optimizations. To solve this challenge we compare three different Evolutionary Algorithms on their capacity to optimize morphologies in modular robotics. We compare two objective-based search algorithms, with MAP-Elites. To understand the benefit of diversity we transition the evolved populations into two difficult environments to see if diversity can have an impact on solving complex environments. In addition, we analyse the genealogical ancestry to shed light on the notion of stepping stones as key to enable high performance. The results show that MAP-Elites is capable of evolving the highest performing solutions in addition to generating the largest morphological diversity. For the transition between environments the results show that MAP-Elites is better at regaining performance by promoting morphological diversity. With the analysis of genealogical ancestry we show that MAP-Elites produces more diverse and higher performing stepping stones than the other objective-based search algorithms. Transitioning the populations to more difficult environments show the utility of morphological diversity, while the analysis of stepping stones show a strong correlation between diversity of ancestry and maximum performance on the locomotion task. The paper shows the advantage of promoting diversity for solving a locomotion task in different environments for modular robotics. By showing that the quality and diversity of stepping stones in Evolutionary Algorithms is an important factor for overall performance we have opened up a new area of analysis and results.
Evolutionary robotics often involves optimization in large, complex search spaces, requiring good population diversity. Recently, measures to actively increase diversity or novelty have been employed in order to get sufficient exploration of the search space either as the sole optimization objective or in combination with some performance measurement. When evolving morphology in addition to the control system, it can be difficult to construct a measure that sufficiently captures the qualitative differences between individuals. In this paper we investigate four diversity measures, applied in a set of evolutionary robotics experiments using an indirect encoding for evolving robot morphology. In the experiments we optimize forward locomotion capabilities of symmetrical legged robots in a physics simulation.
Two distance measures in Cartesian phenotype feature spaces are compared with two methods operating in the space of possible morphology graphs. These measures are used for computing a diversity objective in a multi-objective evolutionary algorithm, and compared to a control case with no diversity objective.
For the given task one of the distance measures shows a clear improvement over the control case in improving the main objectives, while others display better ability to diversify, underlining the difficulty of designing good, general measures of morphological diversity.
This paper proposes an approach to representing robot morphology and control, using a two-level description linked to two different physical axes of development. The bioinspired encoding produces robots with animal-like bilateral limbed morphology with co-evolved control parameters using a central pattern generator-based modular artificial neural network. Experiments are performed on optimizing a simple simulated locomotion problem, using multi-objective evolution with two secondary objectives. The results show that the representation is capable of producing a variety of viable designs even with a relatively restricted set of parameters and a very simple control system. Furthermore, the utility of a cumulative encoding over a non-cumulative approach is demonstrated. We also show that the representation is viable for real-life reproduction by automatically generating CAD files, 3D printing the limbs, and attaching off-the-shelf servomotors.
The reality gap, which often makes controllers evolved in simulation inefficient once transferred onto the physical robot, remains a critical issue in evolutionary robotics (ER). We hypothesize that this gap highlights a conflict between the efficiency of the solutions in simulation and their transferability from simulation to reality: the most efficient solutions in simulation often exploit badly modeled phenomena to achieve high fitness values with unrealistic behaviors. This hypothesis leads to the transferability approach, a multiobjective formulation of ER in which two main objectives are optimized via a Pareto-based multiobjective evolutionary algorithm: 1) the fitness; and 2) the transferability, estimated by a simulation-to-reality (STR) disparity measure. To evaluate this second objective, a surrogate model of the exact STR disparity is built during the optimization. This transferability approach has been compared to two reality-based optimization methods, a noise-based approach inspired from Jakobi's minimal simulation methodology and a local search approach. It has been validated on two robotic applications: 1) a navigation task with an e-puck robot; and 2) a walking task with a 8-DOF quadrupedal robot. For both experimental setups, our approach successfully finds efficient and well-transferable controllers only with about ten experiments on the physical robot.
Author Summary
The evolution of complexity, a central issue of evolutionary theory since Darwin's time, remains a controversial topic. One particular question of interest is how the complexity of an organism's body plan (morphology) is influenced by the complexity of the environment in which it evolved. Ideally, it would be desirable to perform investigations on living organisms in which environmental complexity is under experimental control, but our ability to do so in a limited timespan and in a controlled manner is severely constrained. In lieu of such studies, here we employ computer simulations capable of evolving the body plans of virtual organisms to investigate this question in silico. By evolving virtual organisms for locomotion in a variety of environments, we are able to demonstrate that selecting for locomotion causes more complex morphologies to evolve than would be expected solely due to random chance. Moreover, if increased complexity incurs a cost (as it is thought to do in biology), then more complex environments tend to lead to the evolution of more complex body plans than those that evolve in a simpler environment. This result supports the idea that the morphological complexity of organisms is influenced by the complexity of the environments in which they evolve.
An evolutionary algorithm is used to evolve gaits with the Sony
entertainment robot, AIBO. All processing is handled by the robot's
on-board computer with individuals evaluated using the robot's hardware.
By sculpting the experimental environment, we increase the robustness to
different surface types and different AIBOs. Evolved gaits are faster
than those created by hand. Using this technique we evolve a gait used
in the consumer version of AIBO
We describe a mobile modular robot system that can generate foam to make structural elements. The mobile platform itself is built of CKBot modules and carries extra modules along with a foam generation device. We demonstrate the system synthesizing new robot morphologies: a snake-like robot and a legged robot. We also use the foam structures to encapsulate and pick-up objects and to modify the environment by blocking a door. Our presentation describes the issues that arose in implementing and using this technique.
Proceedings from the ninth International Conference on Artificial Life; papers by scientists of many disciplines focusing on the principles of organization and applications of complex, life-like systems.
Artificial Life is an interdisciplinary effort to investigate the fundamental properties of living systems through the simulation and synthesis of life-like processes. The young field brings a powerful set of tools to the study of how high-level behavior can arise in systems governed by simple rules of interaction. Some of the fundamental questions include: What are the principles of evolution, learning, and growth that can be understood well enough to simulate as an information process? Can robots be built faster and more cheaply by mimicking biology than by the product design process used for automobiles and airplanes? How can we unify theories from dynamical systems, game theory, evolution, computing, geophysics, and cognition?
The field has contributed fundamentally to our understanding of life itself through computer models, and has led to novel solutions to complex real-world problems across high technology and human society. This elite biennial meeting has grown from a small workshop in Santa Fe to a major international conference. This ninth volume of the proceedings of the international A-life conference reflects the growing quality and impact of this interdisciplinary scientific community.
Bradford Books imprint
We present an extensible system for synthesizing and optimizing robot configurations. The system uses a flexible representation for robot configurations based on parameterized modules; this allows us to synthesize mobile and fixed-base robots, including robots with multiple or branching manipulators and free-flying robots. Synthesis of modular robots is also possible with our representation. We use an optimization algorithm based on genetic programming. A distributed architecture is used to spread heavy computational loads across multiple workstations. We take a task-oriented approach to synthesis in which robots are evaluated on a designer-specified task in simulation; flexible planning and control algorithms are thus required so that a wide variety of robots can be evaluated. Our system’s extensibility stems from an object-oriented software architecture that allows new modules, metrics, controllers, and tasks to be easily added. We present two example synthesis tasks: synthesis of a robotic material handler, and synthesis of an antenna pointing system for a mobile robot. We analyze several key issues raised by the experiments and show several important ways in which the system can be extended and improved.
We present the automated design and manufacture of static and locomotion objects in which functionality is obtained purely by the unconstrained 3-D distribution of materials. Recent advances in multimaterial fabrication techniques enable continuous shapes to be fabricated with unprecedented fidelity unhindered by spatial constraints and homogeneous materials. We address the challenges of exploitation of the freedom of this vast new design space using evolutionary algorithms. We first show a set of cantilever beams automatically designed to deflect in arbitrary static profiles using hard and soft materials. These beams were automatically fabricated, and their physical performance was confirmed within 0.5–7.6% accuracy. We then demonstrate the automatic design of freeform soft robots for forward locomotion using soft volumetrically expanding actuator materials. One robot was fabricated automatically and assembled, and its performance was confirmed with 15% error. We suggest that this approach to design automation opens the door to leveraging the full potential of the freeform multimaterial design space to generate novel mechanisms and deformable robots.