Robot Morphology Research Articles

Simultaneous Optimization of Discrete and Continuous Parameters Defining a Robot Morphology and Controller.

The morphology and controller design of robots is often a labor-intensive task performed by experienced and intuitive engineers. Automatic robot design using machine learning is attracting increasing attention in the hope that it will reduce the design workload and result in better-performing robots. Most robots are created by joining several rigid parts and then mounting actuators and their controllers. Many studies limit the possible types of rigid parts to a finite set to reduce the computational burden. However, this not only limits the search space, but also prohibits the use of powerful optimization techniques. To find a robot closer to the global optimal design, a method that explores a richer set of robots is desirable. In this article, we propose a novel method to efficiently search for various robot designs. The method combines three different optimization methods with different characteristics. We apply proximal policy optimization (PPO) or soft actor-critic (SAC) as the controller, the REINFORCE algorithm to determine the lengths and other numerical parameters of the rigid parts, and a newly proposed method to determine the number and layout of the rigid parts and joints. Experiments with physical simulations confirm that when this method is used to handle two types of tasks-walking and manipulation-it performs better than simple combinations of existing methods. The source code and videos of our experiments are available online (https://github.com/r-koike/eagent).

RobotSDF: Implicit Morphology Modeling for the Robotic Arm.

The expression of robot arm morphology is a critical foundation for achieving effective motion planning and collision avoidance in robotic systems. Traditional geometry-based approaches usually suffer from the contradiction between the high demand for computing resources for fine expression and the insufficient detail expression caused by the pursuit of efficiency. The signed distance function addresses these drawbacks due to its ability to handle complex and arbitrary shapes and lower computational requirements. However, conventional robotic morphology methods based on the signed distance function often face challenges when the robot moves dynamically, since robots with different postures are modeled as independent individuals but the postures of robots are infinite. In this paper, we introduce RobotSDF, an implicit morphology modeling approach that can express the robot shape of arbitrary posture precisely. Instead of depicting a whole model of the robot arm, RobotSDF models the robot morphology as integrated implicit joint models driven by joint configurations. In this approach, the dynamic shape change process of the robot is converted into the coordinate transformations of query points within each joint's coordinate system. Experimental results with the Elfin robot demonstrate that RobotSDF can accurately depict robot shapes across different postures up to the millimeter level, which exhibits 38.65% and 66.24% improvement over the Neural-JSDF and configuration space distance field algorithms, respectively, in representing robot morphology. We further verified the efficiency of RobotSDF through collision avoidance in both simulation and actual human-robot collaboration experiments.

Enhancing Robot Learning with Transformer-based Morphology Modeling

Abstract The transformer model has made significant progress in various areas through large-scale training. In contrast, the traditional robot performs a single task, and there is an issue with migrating the strategic model. In this study, a Robot Morphology Learning (RML) method is proposed to enhance efficiency and generalization performance by learning multiple tasks in a transformer model. RML constructs the robot’s morphology as a graph and utilizes a graph neural network to handle graphs of arbitrary connections and sizes, addressing the disparity in state and action space dimensions. RML breaks through the limitation of non-migration of models, realizes efficient training, and improves the generalization performance of models, enabling quick adaptation to new tasks. Experimental results show that the proposed method outperforms previous methods in both multi-task learning and transfer learning experiments.

A model-free method to learn multiple skills in parallel on modular robots

Legged robots are well-suited for deployment in unstructured environments but require a unique control scheme specific for their design. As controllers optimised in simulation do not transfer well to the real world (the infamous sim-to-real gap), methods enabling quick learning in the real world, without any assumptions on the specific robot model and its dynamics, are necessary. In this paper, we present a generic method based on Central Pattern Generators, that enables the acquisition of basic locomotion skills in parallel, through very few trials. The novelty of our approach, underpinned by a mathematical analysis of the controller model, is to search for good initial states, instead of optimising connection weights. Empirical validation in six different robot morphologies demonstrates that our method enables robots to learn primary locomotion skills in less than 15 minutes in the real world. In the end, we showcase our skills in a targeted locomotion experiment.

Comparing Robot Controller Optimization Methods on Evolvable Morphologies.

In this paper, we compare Bayesian Optimization, Differential Evolution, and an Evolution Strategy employed as a gait-learning algorithm in modular robots. The motivational scenario is the joint evolution of morphologies and controllers, where "newborn" robots also undergo a learning process to optimize their inherited controllers (without changing their bodies). This context raises the question: How do gait-learning algorithms compare when applied to various morphologies that are not known in advance (and thus need to be treated as without priors)? To answer this question, we use a test suite of twenty different robot morphologies to evaluate our gait-learners and compare their efficiency, efficacy, and sensitivity to morphological differences. The results indicate that Bayesian Optimization and Differential Evolution deliver the same solution quality (walking speed for the robot) with fewer evaluations than the Evolution Strategy. Furthermore, the Evolution Strategy is more sensitive for morphological differences (its efficacy varies more between different morphologies) and is more subject to luck (repeated runs on the same morphology show greater variance in the outcomes).

Reconfigurable modular soft robots with modulating stiffness and versatile task capabilities

Soft robots have revolutionized machine interactions with humans and the environment to enable safe operations. The fixed morphology of these soft robots dictates their mechanical performance, including strength and stiffness, which limits their task range and applications. Proposed here are modular, reconfigurable soft robots with the capabilities of changing their morphology and adjusting their stiffness to perform versatile object handling and planar or spatial operational tasks. The reconfiguration and tunable interconnectivity between the elemental soft, pneumatically driven actuation units is made possible through integrated permanent magnets with coils. The proposed concept of attaching/detaching actuators enables these robots to be easily rearranged in various configurations to change the morphology of the system. While the potential for these actuators allows for arbitrary reconfiguration through parallel or serial connection on their four sides, we demonstrate here a configuration called ManusBot. ManusBot is a hand-like structure with digits and palm capable of individual actuation. The capabilities of this system are demonstrated through specific examples of stiffness modulation, variable payload capacity, and structure forming for enhanced and versatile object manipulation and operations. The proposed modular, soft robotic system with interconnecting capabilities significantly expands the versatility of operational tasks as well as the adaptability of handling objects of various shapes, sizes, and weights using a single system.

Body and Brain Quality-Diversity in Robot Swarms

In biological societies, complex interactions between the behavior and morphology of evolving organisms and their environment have given rise to a wide range of complex and diverse social structures. Similarly, in artificial counterparts such as swarm-robotics systems, collective behaviors emerge via the interconnected dynamics of robot morphology (sensory-motor configuration), behavior (controller), and environment (task). Various studies have demonstrated morphological and behavioral diversity enables biological groups to exhibit adaptive, robust, and resilient collective behavior across changing environments. However, in artificial (swarm robotic) systems there is little research on the impact of changing environments on morphological and behavioral (body-brain) diversity in emergent collective behavior, and the benefits of such diversity. This study uses evolutionary collective robotics as an experimental platform to investigate the impact of increasing task environment complexity (collective behavior task difficulty) on the evolution and benefits of morphological and behavioral diversity in robotic swarms. Results indicate that body-brain evolution using coupled behavior and morphology diversity maintenance yields higher behavioral and morphological diversity, which is beneficial for collective behavior task performance across task environments. Results also indicate that such behavioral and morphological diversity maintenance coupled with body-brain evolution produces neuro-morpho complexity that does not increase concomitantly with task complexity.

The aesthetics of robot design: towards a classification of morphologies

AbstractRobots are becoming increasingly prevalent in the workplace. As Industry 5.0 pursues human-centric technologies, a greater understanding of what effects aesthetics has on those interacting with robots is needed. This paper sets out robot morphology as a way to characterise key form types, and proposes seven classifications: anthropomorphism, zoomorphism, phytomorphism, artemorphism, functiomorphism, amorphism, and neomorphism. Through an assessment of the current robot aesthetic landscape, design dimensions are identified with examples that can inform future robot design.

Machine learning–driven self-discovery of the robot body morphology

The morphology of a robot is typically assumed to be known, and data from external measuring devices are used mainly for its kinematic calibration. In contrast, we take an agent-centric perspective and ponder the vaguely explored question of whether a robot could learn elements of its morphology by itself, relying on minimal prior knowledge and depending only on unorganized proprioceptive signals. To answer this question, we propose a mutual information–based representation of the relationships between the proprioceptive signals of a robot, which we call proprioceptive information graphs (π-graphs). Leveraging the fact that the information structure of the sensorimotor apparatus is dependent on the embodiment of the robot, we use the π-graph to look for pairwise signal relationships that reflect the underlying kinematic first-order principles applicable to the robot’s structure. In our discussion, we show that analysis of the π-graph leads to the inference of two fundamental elements of the robot morphology: its mechanical topology and corresponding kinematic description, that is, the location and orientation of the robot’s joints. Results from a robot manipulator, a hexapod, and a humanoid robot show that the correct topology and kinematic description can be effectively inferred from their π-graph either offline or online, regardless of the number of links and body configuration.

Gaze-Cues of Humans and Robots on Pedestrian Ways

Delivery robots and personal cargo robots are increasingly sharing space with incidentally co-present persons (InCoPs) on pedestrian ways facing the challenge of socially adequate and safe navigation. Humans are able to effortlessly negotiate this shared space by signalling their skirting intentions via non-verbal gaze cues. In two online-experiments we investigated whether this phenomenon of gaze cuing can be transferred to human–robot interaction. In the first study, participants (n = 92) watched short videos in which either a human, a humanoid robot or a non-humanoid delivery robot moved towards the camera. In each video, the counterpart looked either straight towards the camera or did an eye movement to the right or left. The results showed that when the counterpart gaze cued to their left, also participants skirted more often to the left from their perspective, thereby walking past each other and avoiding collision. Since the participants were recruited in a right-hand driving country we replicated the study in left-hand driving countries (n = 176). Results showed that participants skirted more often to the right when the counterpart gaze cued to the right, and to the left in case of eye movements to the left, expanding our previous result. In both studies, skirting behavior did not differ regarding the type of counterpart. Hence, gaze cues increase the chance to trigger complementary skirting behavior in InCoPs independently of the robot morphology. Equipping robots with eyes can help to indicate moving direction by gaze cues and thereby improve interactions between humans and robots on pedestrian ways.

The Importance of Being Humanoid

A humanoid robot is a particular form of embodied agent. The form that an agent takes has a major impact on how that agent interacts with its environment and how it develops an understanding of that environment through its interactions. In this paper, we explore the importance of humanoid embodiment and we argue that humanoids occupy a special niche in the spectrum of robot forms. In doing so, we highlight the implications for the way a humanoid robot can interact with its environment, including humans, for the manner in which humans interact with humanoid robots, and for a humanoid robot’s capacity to develop cognitive abilities. We also consider the degree to which humanoid robots should approximate humans, addressing robot morphology, appearance, and movement. We emphasize the dual role of humanoid robots as engineering artifacts that can provide services for humans, and as platforms for scientific enquiry into the nature of human cognition. We conclude by highlighting some key research challenges for the discipline of humanoid robotics.

Mechanism Design and Workspace Analysis of a Hexapod Robot With Changeable Morphology

Abstract Here, the morphology of a legged robot refers to the standing/crawling pose of the robot and the forward/backward orientation of the knee, which are related to the configurations of all leg mechanisms. The standing/crawling pose of the robot determines the body height and the leg supporting region size, which are related to the obstacle-traversing and arch-traversing capability. The proper knee orientation can reduce the leg–ground interference risk and help select a good foothold. Therefore, the terrain adaptability can be enhanced if the morphology of the legged robot is changeable. Motivated by this, a hexapod robot capable of morphology conversion is designed in this study. For the leg mechanism, a double-parallelogram transmission mechanism is used to change the forward/backward orientation of the knee. The hexapod robot can transform between the crawling pose and the standing pose and can also transform among four standing morphologies (i.e., the knee–elbow, knee–knee, elbow–knee, and elbow–elbow morphologies). The appropriate robot morphology can be determined according to the terrain type. The lateral reachable body workspaces are derived analytically for different morphologies, which is useful for motion planning. Simulations and experiments are used to verify the design and analysis of the hexapod robot.

An experimental comparison of evolved neural network models for controlling simulated modular soft robots

Voxel-based soft robots (VSRs) are a type of modular robots composed by interconnected soft and deformable blocks, i.e., voxels. Thanks to the softness of their bodies, VSRs may exhibit rich dynamic behaviors. One open question is what type of neural controller is most suitable for a given morphology and sensory apparatus in a given environment. One observation is that artificial neural networks with state may be able to cope with the dynamical nature of VSR bodies and their morphological computation. In this work, we consider four types of controllers, i.e., multilayer perceptrons (MLPs, stateless), recurrent neural networks (RNNs), spiking neural networks (SNNs) without homeostasis, and SNNs with homeostasis. We consider three robot morphologies tested for locomotion, where each morphology is investigated in simulation with three different types and number of sensors. Neural network controllers are optimized with neuroevolution, and the experimental results are compared in terms of effectiveness, efficiency, and generalization ability. In addition, we analyze the resulting behavior of the robots systematically. Our results show that RNNs are typically more effective while MLPs are often the weakest controllers, particularly for robots with few sensors. However, SNNs are more capable in terms of generalization and the mechanism of homeostasis is often beneficial. Finally, we show that RNNs and SNNs with homeostasis produce a more wide variety of behaviors.

The Influence of Robot Traits and Evolutionary Dynamics on the Reality Gap

The elephant in the room for evolutionary robotics is the reality gap. In the history of the field, several studies investigated this phenomenon on fixed robot morphologies where only the controllers evolved. This paper addresses the reality gap in a wider context, in a system where both morphologies and controllers evolve. In this context the morphology of the robots becomes a variable with a currently unknown influence. To examine this influence, we construct a test suite of robots with various morphologies and evolve their controllers for an effective gait. Comparing the simulated and the real-world performance of evolved controllers sampled at different generations during the evolutionary process, we gain new insights into the factors that influence the reality gap.

Robot morphology evolution for automated HVAC system inspections using graph heuristic search and reinforcement learning

The building sector consumes more than 70% of the electricity produced in the U.S., with Heating Ventilation and Air Conditioning (HVAC) systems accounting for half of the electricity consumption. Leaks in HVAC systems have a significant impact on the energy efficiency of buildings, resulting in up to 33% of energy loss. However, the current manual approach to inspection is time-consuming and reactive, leaving room for automation. This paper presents a framework to automatically evolve robot morphology without requiring human intervention to suite any given HVAC and ceiling design. Robot morphologies are optimized using graph heuristic search based on tasks and environment designs, followed by testing of navigation abilities of the best-evolved robot in diverse ceiling environments using reinforcement learning. Tests conducted in robot simulation tools, utilizing realistic HVAC designs retrieved from Building Information Models (BIMs), demonstrate that effortless navigation in complex ceiling environments can be achieved by the evolved robots.

Children’s Digital and Non-Digital Play Practices with Cozmo, the Toy Robot

Children’s Digital and Non-Digital Play Practices with Cozmo, the Toy Robot

Factors Impacting Diversity and Effectiveness of Evolved Modular Robots

In many natural environments, different forms of living organisms successfully accomplish the same task while being diverse in shape and behavior. This biodiversity is what made life capable of adapting to disrupting changes. Being able to reproduce biodiversity in artificial agents, while still optimizing them for a particular task, might increase their applicability to scenarios where human response to unexpected changes is not possible. In this work, we focus on Voxel-based Soft Robots (VSRs), a form of robots that grants great freedom in the design of both morphology and controller and is hence promising in terms of biodiversity. We use evolutionary computation for optimizing, at the same time, morphology and controller of VSRs for the task of locomotion. We investigate experimentally whether three key factors—representation, Evolutionary Algorithm (EA), and environment—impact the emergence of biodiversity and if this occurs at the expense of effectiveness. We devise an automatic machine learning pipeline for systematically characterizing the morphology and behavior of robots resulting from the optimization process. We classify the robots into species and then measure biodiversity in populations of robots evolved in a multitude of conditions resulting from the combination of different morphology representations, controller representations, EAs, and environments. The experimental results suggest that, in general, EA and environment matter more than representation. We also propose a novel EA based on a speciation mechanism that operates on morphology and behavior descriptors and we show that it allows to jointly evolve morphology and controller of effective and diverse VSRs.

Not All Robots are Evaluated Equally: The Impact of Morphological Features on Robots’ Assessment through Capability Attributions

Favorable assessments of social robots are addressed in several research and development attempts because positive attitudes and intentions towards technology are regarded as a necessary prerequisite for usage. To predict a favorable evaluation, it is inevitable to understand the appraisal process and determine crucial variables that affect the evaluative and behavioral consequences of HRI. Robotic morphology has been identified as one of these variables. In the present work, we expand previous work by demonstrating that capability attributions associated with robots’ morphological features explain variations in evaluations. Based on two large picture-based online studies (Study 1, n = 673; Study 2, n = 586) we show that robots with similar morphological features (e.g., robots with arms and grippers) can be clustered along their assigned capabilities, and that these capabilities (e.g., to manipulate objects) explain evaluations of the robots in terms of acceptance and social attributes (i.e., warmth, competence, and discomfort). We discuss whether these initial assessments are relevant to live interactions and how our results can inform robot design.

Morphology and Tension Perception of Cable-Driven Continuum Robots

The operation and control of the cable-driven continuum robot (CDCR) is directly determined by the actuation of cables, and the relationship between the driving length and the tension as well as the morphology of the CDCR has not been deeply researched in previous literature. In this article, a novel methodology for perceiving the morphology, tension, and driving state of the robot is proposed, which can be calculated only by the dynamic driving length/speed of cables without using shape sensors and tension sensors. First, a model of the tension distribution along with the cable path is deduced, which takes into account the influence of the sliding friction. Second, a rigid-flexible coupling dynamic model considering the strain of the cable is established. Then, a nonlinear complementary model between the driving state and the tensions of cables is constructed based on the mechanism of cable actuation, and an efficient solution algorithm is presented. Experiments of a single arm driven by two cables and a three-tandem arm driven by multiple cables were conducted to validate the proposed method. The average errors of the perceiving morphology and tension are 1.85% and 7.26%, respectively, and the transaction between the slack and tensional state of the driving cable is accurately captured. In addition, the hysteresis behavior of the cable actuation is also perceived.

Snake Robot Free Climbing [25 Years Ago

Autonomous snake robot locomotion in rough terrain depends on the robot’s ability to rise from a horizontal position to a vertical, for its ability to climb obstacles. At first sight, lifting <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N</i> body segments seems to require <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</i> ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N</i> <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> )dynamic torque. However, in this article we describe a practical algorithm that requires only <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</i> (1) dynamic torque. The algorithm is applicable to a wide range of snake robot morphologies. The algorithm requires little space, and control is simple, since motion occurs only in a plane. Analysis of the algorithm reveals a strong relation between the maximum dynamic torque required and the joint pitch range. We discuss some consequences for the design of snake robots. For instance, an adjustment of the mass center of the robot’s end segment can reduce the maximum dynamic torque. Implications are studied for some snake robot joint designs, including Dragon, an autonomous snake robot constructed for the study of unconventional locomotion.