Jared M. Moore

Evolutionary Design and Experimental Validation of a Flexible Caudal Fin for Robotic Fish

Designing a robotic fish is a challenging endeavor due to the non-linear dynamics of underwater environments. In this paper, we present an evolutionary computation approach for designing the caudal fin of a carangiform robotic fish. Evolutionary experiments are performed in a simulated environment utilizing a mathematical model to approximate the hydrodynamic motion of a flexible caudal fin. With this model, time-consuming computational fluid dynamic simulations can be avoided while maintaining a physically realistic simulation. Two approaches are employed to maximize a robotic fish’s average velocity. First, a hill-climbing algorithm is applied to find the optimal stiffness for a fixed shape caudal fin. Next, both fin stiffness and shape are simultaneously optimized with a genetic algorithm. Additionally, simulated caudal fins are compared to physically validated fins, which were fabricated with the aid of a 3D printer and tested on a robotic fish prototype. Results show a correlation between evolved results, model predicted behavior, and physical robot performance with some disparity due to the difficulty in accurately approximating real world performance in a simulation environment. Despite the disparity, evolutionary design is shown to be a viable process.

Evolution of station keeping as a response to flows in an aquatic robot

Developing complex behaviors for aquatic robots is a difficult en- gineering challenge due to the uncertainty of an underwater environment. Neuroevolution provides one method of dealing with this type of problem. Artificial neural networks discern different conditions by mapping sensory input to responses, and evolutionary computation provides a training algorithm suitable to the high dimensionality of the problem. In this paper, we present results of applying neuroevolution to an aquatic robot tasked with station keeping, that is, maintaining a given position despite surrounding water flow. The virtual device exposed to evolution is modeled af- ter a physical counterpart that has been fabricated with a 3D printer and tested in physical environments. Evolved behaviors exhibit a variety of unexpected, complex fin/flipper movements that enable the robot to achieve and maintain station, despite water flow from different directions. Moreover, the results show that evolved controllers are able to effectively carry out this task using only infor- mation from a simulated accelerometer and gyroscope, matching the inertial measurement unit (IMU) on the actual robot.

Evolving flexible joint morphologies

Transferring virtual robotic designs into physical robots has become possible with the development of 3D printers. Accurately simulating the performance of real robots in a virtual environment requires modeling a variety of conditions, including the physical composition of the robots themselves. In this paper, we investigate how modeling material flexibility through the use of a passive joint affects the resulting arm morphology and gait of a crawling virtual robot. Results indicate that flexibility can be a beneficial characteristic of robotic morphology design while also providing insight into the benefits of modeling material properties in a simulation environment.

Evaluating the Effect of a Flexible Spine on the Evolution of Quadrupedal Gaits

Animals demonstrate a level of agility currently unmatched in their robotic counterparts. The elasticity of muscles and tendons increase not only performance, but also the efficiency of movements. In contrast, robots are often constructed with rigid components connected by motors. However, recently compliant actuators and materials have been introduced to enhance robot designs, emulating the flexibility of natural organisms. In this paper, we incorporate passive flexibility into the spine of a quadruped animat and employ computational evolution to generate gaits. Results indicate that spine flexibility significantly increases both performance and efficiency of evolved individuals. Moreover, evolving the degree of spine flexibility along with artificial neural network controllers produces the highest performing solutions.

Evolving joint-level control with digital muscles

The neuromuscular systems of animals are governed by extremely complex networks of control signals, sensory feedback loops, and mechanical interactions. Morphology and control are inherently intertwined. In the case of animal joints, groups of muscles work together to provide power and stability to move limbs in a coordinated manner. In contrast, many robot controllers handle both high-level planning and low-level control of individual joints. In this paper, we propose a joint-level control method, called digital muscles, that operates in a manner analogous to biological muscles, yet is abstract enough to apply to conventional robotic joints. An individual joint is controlled by multiple muscle nodes, each of which responds to a control signal according to a node-specific activation function. Evolving the physical orientation of muscle nodes and their respective activation functions enables relatively complex and coordinated gaits to be realized with simple high-level control. Even using a sinusoid as the high-level control signal, we demonstrate the evolution of effective gaits for a simulated quadruped. The proposed model realizes a control strategy for governing the behavior of individual joints, and can be coupled with a high-level controller that focuses on decision making and planning.

Exploring the Role of the Tail in Bipedal Hopping through Computational Evolution

Bipedal hopping has evolved as a mode of terrestrial locomotion in relatively few mammalian species. Despite large differences in body size, habitat use, and having evolved independently, all species that use bipedal hopping have remarkably similar limb morphology and posture. In addition, these species all have relatively long tails, presumably to assist in maintaining stability. However, the evolution of this behavior, and specifically the role of the tail, is not well understood. In this paper, we explore the evolution of bipedal hopping in a simulated animat, using a relatively simple musculoskeletal model and a rigid-body physics simulation environment. Results indicate that characteristically different hopping gaits evolve with alterations to the morphology, including the structure and actuation of the tail. Many of the the results are consistent with behaviors and morphologies observed in natural organisms. However, in some cases effective hopping evolved despite key differences from nature, potentially inspiring new design approaches in robotic and biomechanical systems.

Effect of animat complexity on the evolution of hierarchical control

Animal movements are realized by a combination of high-level control from the nervous system and joint-level movement provided by the musculoskeletal system. The digital muscle model (DMM) emulates the low-level musculoskeletal system and can be combined with a high-level artificial neural network (ANN) controller forming a hybrid control strategy. Previous work has shown that, compared to ANN-only controllers, hybrid ANN/DMM controllers exhibit similar performance with fewer synapses, suggesting that some computation is offloaded to the low-level DMM. An open question is how the complexity of the robot, in terms of the number of joints, affects the evolution of the ANN control structure. We explore this question by evolving both hybrid controllers and ANN-only controllers for worm-like animats of varying complexity. Specifically, the number of joints in the worms ranges from 1 to 12. Consistent with an earlier study, the results demonstrate that, in most cases, hybrid ANN/DMM controllers exhibit equal or better performance than ANN-only controllers. In addition, above a threshold for animat complexity (number of joints), the ANNs for one variant of the hybrid controllers have significantly fewer connections than the ANN-only controllers.

Evolution of joint-level control for quadrupedal locomotion

We investigate a hierarchical approach to robot control inspired by joint-level control in animals. The method combines a high-level controller, consisting of an artificial neural network (ANN), with joint-level controllers based on digital muscles. In the digital muscle model (DMM), morphological and control aspects of joints evolve concurrently, emulating the musculoskeletal system of natural organisms. We introduce and compare different approaches for connecting outputs of the ANN to DMM-based joints. We also compare the performance of evolved animats with ANN-DMM controllers with those governed by only high-level (ANN-only) and low-level (DMM-only) controllers. These results show that DMM-based systems outperform their ANN-only counterparts while also exhibiting less complex ANNs in terms of the number of connections and neurons. The main contribution of this work is to explore the evolution of artificial systems where, as in natural organisms, some aspects of control are realized at the joint level.

Applying evolutionary computation to harness passive material properties in robots

Evolution has produced a wide variety of organisms that interact with their physical environment through musculoskeletal systems. Movements are often aided by passive characteristics of an organisms body and the inherent flexibility of muscles. Emulating these characteristics in a robot can potentially increase performance and maneuverability, but requires finding effective solutions among an infinite set of possible morphology and controller combinations. Evolutionary computation provides a means to explore this large search space. However, developing simulation models to account for these material properties presents challenges. In this paper, we present an overview of the challenges in implementing such an evolutionary approach. We also present preliminary results demonstrating the effectiveness of our proposed methods.

Evolution of an amphibious robot with passive joints

Passive joints provide a means to reduce the mechanical complexity of a robot because they do not require direct actuation from a motor. However, the inclusion of such components complicates the development process, as their behavior is highly dependent on external stimuli in combination with actuation of other components. In this paper, we describe a study on the evolution of morphological characteristics and controller parameters for an amphibious robot with passive arm joints. Results show that this approach is able to exploit the properties of passive joints, producing effective locomotion in both aquatic and terrestrial environments. Evolved solutions demonstrate a strong coupling between fin morphology and control strategy with respect to performance.