Search

This work concerns the application of physics-informed neural networks to the modeling and control of complex robotic systems. Achieving this goal requires extending physics-informed neural networks to handle nonconservative effects. These learned models are proposed to combine with model-based controllers originally developed with first-principle models in mind. By combining standard and new techniques, precise control performance can be achieved while proving theoretical stability bounds. These validations include real-world experiments of motion prediction with a soft robot and trajectory tracking with a Franka Emika Panda manipulator., Learning & Autonomous Control

Suitable representations of dynamical systems can simplify their analysis and control. On this line of thought, this article aims to answer the following question: Can a transformation of the generalized coordinates under which the actuators directly perform work on a subset of the configuration variables be found? We not only show that the answer to this question is yes but also provide necessary and sufficient conditions. More specifically, we look for a representation of the configuration space such that the right-hand side of the dynamics in Euler-Lagrange form becomes [\boldsymbol{I}\; \boldsymbol{O}]{T}\boldsymbol{u}, being \boldsymbol{u} the system input. We identify a class of systems, called collocated, for which this problem is solvable. Under mild conditions on the input matrix, a simple test is presented to verify whether a system is collocated or not. By exploiting power invariance, we provide necessary and sufficient conditions that a change of coordinates decouples the input channels if and only if the dynamics is collocated. In addition, we use the collocated form to derive novel controllers for damped underactuated mechanical systems. To demonstrate the theoretical findings, we consider several Lagrangian systems with a focus on continuum soft robots., Learning & Autonomous Control

This letter concerns control-oriented and structure-preserving learning of low-dimensional approximations of high-dimensional physical systems, with a focus on mechanical systems. We investigate the integration of neural autoencoders in model order reduction, while at the same time preserving Hamiltonian or Lagrangian structures. We focus on extensively evaluating the considered methodology by performing simulation and control experiments on large mass-spring-damper networks, with hundreds of states. The empirical findings reveal that compressed latent dynamics with less than 5 degrees of freedom can accurately reconstruct the original systems' transient and steady-state behavior with a relative total error of around 4%, while simultaneously accurately reconstructing the total energy. Leveraging this system compression technique, we introduce a model-based controller that exploits the mathematical structure of the compressed model to regulate the configuration of heavily underactuated mechanical systems., Learning & Autonomous Control

Model-based strategies are a promising solution to the grand challenge of equipping continuum soft robots with motor intelligence. However, finite-dimensional models of these systems are inherently inaccurate, thus posing pressing robustness concerns. Moreover, the actuation space of soft robots is usually limited. This article aims at solving both these challenges by proposing a robust model-based strategy for the shape control of soft robots with system uncertainty and input saturation. The proposed architecture is composed of two key components. First, we propose an observer that estimates deviations between the theoretical model and the soft robot, ensuring that the estimation error converges to zero within finite time. Second, we introduce a sliding mode controller to regulate the soft robot shape while fulfilling saturation constraints. This controller uses the observer's output to compensate for the deviations between the real system and the established model. We prove the convergence of the closed-loop with theoretical analysis and the method's effectiveness with simulations and experiments., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

The complexity of the human shoulder girdle enables the large mobility of the upper extremity, but also introduces instability of the glenohumeral (GH) joint. Shoulder movements are generated by coordinating large superficial and deeper stabilizing muscles spanning numerous degrees-of-freedom. How shoulder muscles are coordinated to stabilize the movement of the GH joint remains widely unknown. Musculoskeletal simulations are powerful tools to gain insights into the actions of individual muscles and particularly of those that are difficult to measure. In this study, we analyze how enforcement of GH joint stability in a musculoskeletal model affects the estimates of individual muscle activity during shoulder movements. To estimate both muscle activity and GH stability from recorded shoulder movements, we developed a Rapid Muscle Redundancy (RMR) solver to include constraints on joint reaction forces (JRFs) from a musculoskeletal model. The RMR solver yields muscle activations and joint forces by minimizing the weighted sum of squared-activations, while matching experimental motion. We implemented three new features: first, computed muscle forces include active and passive fiber contributions; second, muscle activation rates are enforced to be physiological, and third, JRFs are efficiently formulated as linear functions of activations. Muscle activity from the RMR solver without GH stability was not different from the computed muscle control (CMC) algorithm and electromyography of superficial muscles. The efficiency of the solver enabled us to test over 3600 trials sampled within the uncertainty of the experimental movements to test the differences in muscle activity with and without GH joint stability enforced. We found that enforcing GH stability significantly increases the estimated activity of the rotator cuff muscles but not of most superficial muscles. Therefore, a comparison of shoulder model muscle activity to EMG measurements of superficial muscles alone is i, Human-Robot Interaction, Learning & Autonomous Control, Biomechatronics & Human-Machine Control

We show that large language models (LLMs), such as ChatGPT, can guide the robot design process, on both the conceptual and technical level, and we propose new human–AI co-design strategies and their societal implications., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

The spread of an epidemic over a population is influenced by a multitude of factors having both spatial and temporal nature, which are hard to completely capture using first principle methods. This paper concerns regional forecasting of SARS-Cov-2 infections 1 week ahead using machine learning. We especially focus on the Dutch case study for which we develop a municipality-level COVID-19 dataset. We propose to use a novel spatiotemporal graph neural network architecture to perform the predictions. The developed model captures the spread of infectious diseases within municipalities over time using Gated Recurrent Units and the spatial interactions between municipalities using GATv2 layers. To the best of our knowledge, this model is the first to incorporate sewage data, the stringency index, and commuting information into GNN-based infection prediction. In experiments on the developed real-world dataset, we demonstrate that the model outperforms simple baselines and purely spatial or temporal models for the COVID-19 wild type, alpha, and delta variants. More specifically, we obtain an average R2 of 0.795 for forecasting infections and of 0.899 for predicting the associated trend of these variants., Learning & Autonomous Control

Performing precise, repetitive motions is essential in many robotic and automation systems. Iterative learning control (ILC) allows determining the necessary control command by using a very rough system model to speed up the process. Functional iterative learning control is a novel technique that promises to solve several limitations of classic ILC. It operates by merging the input space into a large functional space, resulting in an over-determined control task in the iteration domain. In this way, it can deal with systems having more outputs than inputs and accelerate the learning process without resorting to model discretizations. However, the framework lacks so far a validation in experiments. This paper aims to provide such experimental validation in the context of robotics. To this end, we designed and built a one-link flexible arm that is actuated by a stepper motor, which makes the development of an accurate model more challenging and the validation closer to the industrial practice. We provide multiple experimental results across several conditions, proving the feasibility of the method in practice., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control, Medical Instruments & Bio-Inspired Technology

From a functional standpoint, classic robots are not at all similar to biological systems. If compared with rigid robots, animals' bodies look overly redundant, imprecise, and weak. Nevertheless, animals can still perform a vast range of activities with unmatched effectiveness. Many studies in biomechanics have pointed to the elastic and compliant nature of the musculoskeletal system as a fundamental ingredient explaining this gap. Thus, to reach performance comparable to nature, elastic elements have been introduced in rigid-bodied robots, leading to articulated soft robotics [1] (see 'Summary'). In continuum soft robotics, this concept is brought to an extreme. Here, softness is not concentrated at the joint level but instead distributed across the whole structure. As a result, soft robots (henceforth, omitting the adjective continuum) are entirely made of continuously deformable elements. This design solution aims to bring robots closer to invertebrate animals and the soft appendices of vertebrate animals (for example, an elephant's trunk and the tail of a monkey). Several soft robotic hardware platforms have been proposed with increasingly higher reliability and functionalities. In this process, considerable attention has been devoted to the technological side of the problem, leading to a large assortment of hardware solutions. In turn, this abundance opened up the challenge of developing effective control strategies that can manage the soft body and exploit its embodied intelligence., Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

Industrial automation calls for precise tasks with cycle times reduced to the minimum. At the same time, when handling delicate products such as fruits and vegetables, accelerations must be kept low to keep interaction forces under a certain threshold to avoid damage. This trade-off hinders the penetration of automation in many relevant application fields. This paper investigates using soft technology to solve this challenge. We propose the FinFix gripper, a non-anthropomorphic soft gripper capable of handling delicate objects at high acceleration using a contact-reactive grasping approach. This gripper has two entirely passive sensorized fingers that establish contact and two active fingers that are actuated pneumatically through a rigid mechanism allowing for rapid closure. We provide exhaustive experimental validation by connecting the gripper to a delta robot. The system can reliably execute pick-and-place cycles in ∼1 s when the distance between the pick and the place locations is 400 mm, resulting in a peak speed of ∼10ms . None of the fragile objects used during the experiments showed any damage. The only information needed is a rough estimation of the object's position to be grasped and a contact event to trigger the reflex. The test results show that the gripper can hold fragile objects during lateral accelerations of 10g., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control, Medical Instruments & Bio-Inspired Technology

Elephants and other animals heavily rely on the sense of smell to operate. Soft robots would also benefit from an artificial sense of smell, which could be helpful in typical soft robotic tasks such as search and rescue, pipe inspection, and all the tasks involving unstructured environments. This work proposes an artificial nose on a soft robotic arm that ensures separate smell concentration readings. We propose designing the nose to generate a one-to-one matching between the sensors' inputs and the actuators. This design choice allows us to implement a simple control strategy tailored to reach a dynamically varying smell in the environment, which we validate on a two-segment tendon-driven soft robotic arm equipped with the proposed artificial nose. We also propose and validate in simulation a control strategy for reaching tasks in the case of a stationary smell, Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

The success of soft robots in displaying emergent behaviors is tightly linked to the compliant interaction with the environment. However, to exploit such phenomena, proprioceptive sensing methods which do not hinder their softness are needed. In this work we propose a new sensing approach for soft underwater slender structures based on embedded pressure sensors and use a learning-based pipeline to link the sensor readings to the shape of the soft structure. Using two different modeling techniques, we compare the pose reconstruction accuracy and identify the optimal approach. Using the proprioceptive sensing capabilities we show how this information can be used to assess the swimming performance over a number of metrics, namely swimming thrust, tip deflection, and the traveling wave index. We conclude by demonstrating the robustness of the embedded sensor on a free swimming soft robotic squid swimming at a maximum velocity of 9.5 cm/s, with the absolute tip deflection being predicted within an error less than 9% without the aid of external sensors., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

Soft robot are celebrated for their propensity to enable compliant and complex robot-environment interactions. Soft robotic manipulators, or slender continuum structure robots have the potential to exploit these interactions to enable new exploration and manipulation capabilities and safe human-robot interactions. However, the interactions, or perturbations by external forces cause the soft structure to deform in an infinite degree of freedom (DOF) space. To control such system, reduced order models are needed; typically models consider piecewise sections of constant curvature although external forces often deform the structure out of the constant curvature hypothesis. In this work we perform an analysis of the trade-off between computational treatability and modelling accuracy. We then propose a new kinematic model, the Piecewise Affine Curvature (PAC) which we validate theoretically and experimentally showing that this higher-order model better captures the configuration of a soft continuum body robot when perturbed by the external forces. In comparison to the current state of the art Piecewise Constant Curvature (PCC) model we demonstrate up to 30% reduction in error for the end position of a soft continuum body robot., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

Land-based mitigation technologies and practices (LMTs) are critical for achieving the Paris Agreement’s aim of avoiding dangerous climate change by limiting the rise in average global surface temperatures. We developed a detailed two-level classification and analysis of the barriers to the adoption and scaling up of LMTs. The review suggests that afforestation/reforestation and forest management are LMTs with wide application and high potential across all continents. BECCS (bioenergy with carbon capture and storage) and biochar have a higher potential in higher-income countries in the short term, due to the availability of technology, funding, and low-cost biomass value chains. Although most LMTs can be cost-effective across multiple world regions, limited knowledge concerning their implementation and insufficient financing appear to be the main barriers to their large-scale deployment. Without considering gender and the rights of marginalised and Indigenous Peoples, the large-scale deployment of LMTs can further aggravate existing inequalities. Therefore, the social and institutional implications of LMTs need to be better understood to improve their public acceptance and reduce negative impacts. An integrated system approach is necessary to strike a balance between ambitious land-based mitigation targets and socioeconomic and environmental goals., Learning & Autonomous Control, Organisation & Governance

Fully exploiting soft robots' capabilities requires devising strategies that can accurately control their movements with the limited amount of control sources available. This task is challenging for reasons including the hard-to-model dynamics, the system's underactuation, and the need of using a prominent feedforward control action to preserve the soft and safe robot behavior. To tackle this challenge, this letter proposes a purely feedforward iterative learning control algorithm that refines the torque action by leveraging both the knowledge of the model and data obtained from past experience. After presenting a 3D polynomial description of soft robots, we study their intrinsic properties, e.g., input-to-state stability, and we prove the convergence of the controller coping with locally Lipschitz nonlinearities. Finally, we validate the proposed approach through simulations and experiments involving multiple systems, trajectories, and in the case of external disturbances and model mismatches., Learning & Autonomous Control

Animals rely on the elasticity of their tendons and muscles to execute robust and efficient locomotion patterns for a vast and continuous range of velocities. Replicating such capabilities in artificial systems is a long-lasting challenge in robotics. By taking advantage of a pitch dynamics decoupling spring potential, this work aims to provide design rules and a control strategy to generate dynamic, efficient locomotion patterns in quadrupeds moving in a sagittal plane. We rely on nonlinear modal theory, which provides the tools to characterize continuous families of efficient oscillations in nonlinear mechanical systems. We provide simulations of an elastic quadruped showing that the proposed solution can robustly excite efficient locomotion patterns under non-ideal conditions., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

Electrically-actuated continuum soft robots based on Handed Shearing Auxetics (HSAs) promise rapid actuation capabilities while preserving structural compliance. However, the foundational models of these novel actuators required for precise control strategies are missing. This paper proposes two key components extending discrete Cosserat rod model (DCM) to allow for modeling HSAs. First, we propose a mechanism for incorporating the auxetic trajectory into DCM dynamical simulations. We also propose an implementation of this extension as a plugin for the Elastica simulator. Second, we introduce a Selective Piecewise Constant Strain (SPCS) kinematic parameterization that can describe an HSA segment's shape with fewer configuration variables. We verify both theoretical contributions experimentally. The simulator is used to replicate experimental data of the mechanical characterization of HSA rods. For the second component, we attach motion capture markers at various points to a parallel HSA robot and find that the shape of the HSAs can be kinematically represented with an average accuracy of 0.3 mm for positions and 0.07 rad for orientations., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

In this paper, we first discuss the challenges related to habitat monitoring and review possible robotic solutions. Then, we propose a framework to perform terrestrial habitat monitoring exploiting the mobility of legged robotic systems. The idea is to provide the robot with the Natural Intelligence introduced as the combination of the environment in which it moves, the intelligence embedded in the design of its body, and the algorithms composing its mind. This approach aims to solve the challenges of deploying robots in real natural environments, such as irregular and rough terrains, long-lasting operations, and unexpected collisions, with the final objective of assisting humans in assessing the habitat conservation status. Finally, we present examples of robotic monitoring of habitats in four different environments: forests, grasslands, dunes, and screes., Learning & Autonomous Control

Soft robots are intrinsically underactuated mechanical systems that operate under uncertainties and disturbances. In these conditions, this letter proposes two versions of PID-like control laws with a saturated integral action for the particularly challenging shape regulation task. The closed-loop system is asymptotically stabilized and matched constant disturbances are rejected using a very reduced amount of system information for control implementation. Stability is assessed on the underactuated dynamic model through the Invariant Set Theorem for two relevant classes of soft robots, i.e., elastically decoupled and elastically dominated soft robots. Extensive simulation results validate the proposed controllers., Learning & Autonomous Control

This letter investigates the stability properties of the soft inverted pendulum with affine curvature - a template model for nonlinear control of underactuated soft robots. We look at how changes in physical parameters affect stability and equilibrium. We give conditions under which zero dynamics corresponding to a collocated choice of the output is (locally or globally) stable or unstable. We leverage these results to design a switching controller that stabilizes a class of nonlinear equilibria of the pendulum, which can drive the system from one equilibrium to another., Learning & Autonomous Control

Intelligent manufacturing is becoming increasingly important due to the growing demand for maximizing productivity and flexibility while minimizing waste and lead times. This work investigates automated secondary robotic food packaging solutions that transfer food products from the conveyor belt into containers. A major problem in these solutions is varying product supply which can cause drastic productivity drops. Conventional rule-based approaches, used to address this issue, are often inadequate, leading to violation of the industry's requirements. Reinforcement learning, on the other hand, has the potential of solving this problem by learning responsive and predictive policy, based on experience. However, it is challenging to utilize it in highly complex control schemes. In this paper, we propose a reinforcement learning framework, designed to optimize the conveyor belt speed while minimizing interference with the rest of the control system. When tested on real-world data, the framework exceeds the performance requirements (99.8% packed products) and maintains quality (100% filled boxes). Compared to the existing solution, our proposed framework improves productivity, has smoother control, and reduces computation time., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

Today's use of large-scale industrial robots is enabling extraordinary achievement on the assembly line, but these robots remain isolated from the humans on the factory floor because they are very powerful, and thus dangerous to be around. In contrast, the soft robotics research community has proposed soft robots that are safe for human environments. The current state of the art enables the creation of small-scale soft robotic devices. In this article we address the gap between small-scale soft robots and the need for human-sized safe robots by introducing a new soft robotic module and multiple human-scale robot configurations based on this module. We tackle large-scale soft robots by presenting a modular and reconfigurable soft robotic platform that can be used to build fully functional and untethered meter-scale soft robots. These findings indicate that a new wave of human-scale soft robots can be an alternative to classic rigid-bodied robots in tasks and environments where humans and machines can work side by side with capabilities that include, but are not limited to, autonomous legged locomotion and grasping., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work, Learning & Autonomous Control

The nature of continuum soft robots calls for novel perception solutions, which can provide information on the robot's shape while not substantially modifying their bodies' softness. One way to achieve this goal is to develop innovative and completely deformable sensors. However, these solutions tend to be less reliable than classic sensors for rigid robots. As an alternative, we consider here the use of monocular cameras. By admitting a small rigid component in our design, we can leverage well-established solutions from mobile robotics. We propose a shape sensing strategy that combines a SLAM algorithm with nonlinear optimization based on the robot's kinematic model. We prove the method's effectiveness in simulation and with experiments of a single-segment continuous soft robot with a camera mounted to the tip. We achieve mean relative translational errors below 9% simulations and experiments alike, and as low as 0.5% on average for some simulation conditions., Accepted Author Manuscript, Learning & Autonomous Control

Adding elastic elements to the mechanical structure should enable robots to perform efficient oscillatory tasks. Still, even characterizing natural oscillations in nonlinear systems is a challenge in itself, which nonlinear modal theory promises to solve. Therein eigenmanifolds generalize eigenspaces to mechanical systems with non-Euclidean metrics and thus characterize families of oscillations that are autonomous evolutions of the robot. Eigenmanifolds likewise provide a framework for deriving feedback controllers to excite and sustain these oscillations. Nevertheless, these results have been so far essentially theoretical. They have been applied on relatively low dimensional systems and almost exclusively in simulation. We aim to bridge the theory to the real-world gap with the present work and show that we can excite nonlinear modes in complex systems. To this end, we propose control strategies that can simultaneously stabilize numerically evaluated eigenmanifolds and sustain oscillations in the presence of dissipation. We then focus on the KUKA iiwa with simulated parallel springs as an example of the highly nonlinear and articulated system. We calculate all the nonlinear modes of the system, and we use the proposed strategies to excite the associated natural oscillations., Accepted Author Manuscript, Learning & Autonomous Control

The intrinsically underactuated and nonlinear nature of continuum soft robots makes the derivation of provably stable feedback control laws a challenging task. Most of the works so far circumvented the issue either by looking at coarse fully-actuated approximations of the dynamics or by imposing quasi-static assumptions. In this letter, we move a step in the direction of controlling generic soft robots taking explicitly into account their underactuation. A class of soft robots that have no direct elastic couplings between the dynamics of actuated and unactuated coordinates is identified. Considering the actuated variables as output, we prove that the system is minimum phase. We then propose regulators that implement different levels of model compensation. The stability of the associated closed-loop systems is formally proven by Lyapunov/LaSalle techniques, taking into account the nonlinear and underactuated dynamics. Simulation results are reported for two models of 2D and 3D soft robots., Accepted Author Manuscript, Learning & Autonomous Control

When an epidemic spreads into a population, it is often impractical or impossible to continuously monitor all subjects involved. As an alternative, we propose using algorithmic solutions that can infer the state of the whole population from a limited number of measures. We analyze the capability of deep neural networks to solve this challenging task. We base our proposed architecture on Graph Convolutional Neural Networks. As such, it can reason on the effect of the underlying social network structure, which is recognized as the main component in spreading an epidemic. The proposed architecture can reconstruct the entire state with accuracy above 70%, as proven by two scenarios modeled on the CoVid-19 pandemic. The first is a generic homogeneous population, and the second is a toy model of the Boston metropolitan area. Note that no retraining of the architecture is necessary when changing the model., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

Citizens are expected to play a significant role to the current energy transition in Europe, such as through prosumerism and collective initiatives for energy efficiency. While there are many platforms for domestic energy analytics and for engaging citizens and transition stakeholders on energy topics, context-specific information is frequently lacking. This article outlines the development of an Interactive Policy Platform that aims to provide contextualized, impact-driven, and ready-to-use information on the role of citizen initiatives in the energy and low-carbon transition in Europe. Specifically, it will help researchers, policymakers, and citizens to explore different dimensions of energy citizenship, understand the decarbonization potentials of diverse clusters of citizens, and identify the conditions under which citizen-led energy initiatives are currently operating. The Platform will be co-designed together with a sample of its future users, ensuring the usability of its interface and the relevance of the provided information. Ultimately, the Platform is envisioned to help transition stakeholders understand and support initiatives related to energy citizenship around Europe, thus contributing to the EU's promise of a just and inclusive decarbonization., Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., System Engineering, Organisation & Governance, Learning & Autonomous Control, Policy Analysis

Biology provides many examples of how body adaption can be used to achieve a change in functionality. The feather star, an underwater crinoid that uses feather arms to locomote and feed, is one such system; it releases its arms to distract prey and vary its maneuverability to help escape predators. Using this crinoid as inspiration, we develop a robotic system that can alter its interaction with the environment by changing its morphology. We propose a robot that can actuate layers of flexible feathers and detach them at will. We first optimize the geometric and control parameters for a flexible feather using a hydrodynamic simulation followed by physical experiments. Second, we provide a theoretical framework for understanding how body change affects controllability. Third, we present a novel design of a soft swimming robot ( Figure 1 ) with the ability of changing its morphology. Using this optimized feather and theoretical framework, we demonstrate, on a robotic setup, how the detachment of feathers can be used to change the motion path while maintaining the same low-level controller., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

Implementing dynamic legged locomotion entails stabilizing oscillatory behaviors in complex mechanical systems. Whenever possible, locomotion algorithms should also exploit the improved capabilities of elastic elements added to the structure to improve efficiency and robustness. This work aims to shed some light on implementing generic dynamic locomotion by stabilizing nonlinear modes. The nonlinear modal analysis extends the linear modal theory to nonlinear systems and thus characterizes the oscillations that a robot can execute as autonomous evolutions. We execute forward hopping motions with a single segmented elastic leg as the first step towards generic modal locomotion. We propose a locomotion algorithm that exploits the modes of an extension of the SLIP model. We develop this strategy to generalize to other robotic systems, and we extensively validate it with experiments on an elastically actuated segmented leg., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

The control possibilities for soft robots have long been hindered by the lack of accurate yet computationally treatable dynamic models of soft structures. Polynomial curvature models propose a solution to this quest for continuum slender structures. Nevertheless, the results produced with this class of models have been so far essentially theoretical. With the present work, we aim to provide a much-needed experimental validation to these recent theories. To this end, we focus on soft tentacles immersed in water. First, we propose an extension of the affine curvature model to underwater structures, considering the drag forces arising from the fluid-solid interaction. Then, we extensively test the model's capability to describe the system behavior across several shapes and working conditions. Finally, we validate model-based control policies, proposing and solving an optimal control problem for directional underwater swimming. Using the model we show an average increase of more than 3.5 times the swimming speed of a sinusoidal baseline controller, with some tentacles showing an improvement in excess of 5.5 times the baseline., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

Nowadays, harvesting delicate and high-value fruits, vegetables and edible fungi requires a large input of manual human labor. The relatively low wages and many health problems the workforce faces make this profession increasingly unpopular. Meanwhile, robotic systems that selectively harvest crops are being developed. Whilst the moving platform, manipulator, and recognition systems of such robots are studied the past few decades, research on the gripping end of such robots is only recently growing. This study analyses the state-of-the-art of soft grippers for crop handling and harvesting, reporting their quantitative and qualitative characteristics. Seventy-eight grippers are retrieved from the academic literature and compared with each other in terms of their design and reported performance, more specifically grasping and detachment methods, materials used, type of actuators and sensors employed, and the control of the gripping procedure. In addition, the identified grippers are classified into 13 distinct soft grasping technology categories. Moreover, the retrieved papers are analyzed with respect to their publication date and country of origin to observe the recent growth in the field. Furthermore, a subset of soft grippers is identified that was tested on the task of selectively harvesting crops, where grip and detachment success rates and plant and crop damage are compared., Medical Instruments & Bio-Inspired Technology, Learning & Autonomous Control

Embedding elastic elements into legged robots through mechanical design enables highly efficient oscillating patterns that resemble natural gaits. However, current trajectory planning techniques miss the opportunity of taking advantage of these natural motions. This work proposes a locomotion planning method that aims to unify traditional trajectory generation with modal oscillations. Our method utilizes task-space linearized modes for generating center of mass trajectories on the sagittal plane. We then use nonlinear optimization to find the gait timings that match these trajectories within the Divergent Component of Motion planning framework. This way, we can robustly translate the modes-aware centroidal motions into joint coordinates. We validate our approach with promising results and insights through experiments on a compliant quadrupedal robot., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

Damping injection is a well-studied tool in nonlinear control theory to stabilize and shape the transient of mechanical systems. Interestingly, the injection of coupled damping yielding gyroscopic forces has received far less attention. This letter aims to fill this gap for gyroscopic forces that couple actuated and unactuated coordinates. First, we establish sufficient conditions for the stability of the closed loop. Then, we provide analytic results proving that injecting coupled damping may improve the closed-loop performance. We illustrate the results via the stabilization of three mechanical systems., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control, Team Azita Dabiri

Unmanned Aerial Vehicles (UAVs) are widely used for environmental surveying and exploration thanks to their maneuverability and accessibility. Until recently, however, these platforms were mainly used as passive systems that observe their environments visually and do not interact physically. The capability of UAVs to physically interact with their environment, also known as Aerial Manipulators (AMs), allows them to do a wider variety of tasks. These tasks include contact inspection, manipulation of objects, and more. To successfully interact with the environment, the AM must compensate for the contact-induced disturbance forces. One approach is to estimate the contact force and compensate for it within the control approach. This work introduces a framework to estimate the contact force at the End-Effector (EE) using only state measurements of the generic AM. Further, the evaluation of the framework in a simulation of an AM with a tendon-driven robotic arm shows that it precisely estimates the contact force., Control & Simulation, Learning & Autonomous Control

Sensing the shape of continuum soft robots without obstructing their movements and modifying their natural softness requires innovative solutions. This letter proposes to use magnetic sensors fully integrated into the robot to achieve proprioception. Magnetic sensors are compact, sensitive, and easy to integrate into a soft robot. We also propose a neural architecture to make sense of the highly nonlinear relationship between the perceived intensity of the magnetic field and the shape of the robot. By injecting a priori knowledge from the kinematic model, we obtain an effective yet data-efficient learning strategy. We first demonstrate in simulation the value of this kinematic prior by investigating the proprioception behavior when varying the sensor configuration, which does not require us to re-train the neural network. We validate our approach in experiments involving one soft segment containing a cylindrical magnet and three magnetoresistive sensors. During the experiments, we achieve mean relative errors of 4.5%., Special issue on "Advanced Materials and Processes for Soft Robotics", Learning & Autonomous Control

This paper proposes a model-based control design approach for a broad class of soft robots, having their elastic field dominating gravity in the unactuated coordinates. To this end, we consider finite-dimensional dynamic models obtained from approximations of the system's energy. Then, we propose a general control architecture that can stabilize soft robots based on potential energy shaping. We discuss three specializations of this general architecture: a PD with mixed feedback-feedforward gravity compensation, a PD with feedforward compensation, and a saturated version of the latter. We provide a physical interpretation of the controllers, and we illustrate their applicability through simulations., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control, Team Azita Dabiri

Many are the challenges that make robotic manipulation of deformable objects such a complex task. For example, to properly plan and execute a control action, a robot needs to understand how external forces will modify the deformation states of the object. Creating such an internal representation is even more complex in the typical situation where the robot is interacting for the first time with the object. In this paper, we look at this challenge when controlling the deformation states of a planar and slender object. Leveraging soft robots' modelling and control, we show that the only non-geometrical information needed to perform this task is the stiffness distribution. We thus propose a strategy to learn this function from a single interaction with the object, testing it experimentally. We then propose a closed-loop controller that exploits this learned information to perform the manipulation task and test it with simulations., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

When an epidemic spreads into a population, it is often impractical or impossible to continuously monitor all subjects involved. As an alternative, we propose using algorithmic solutions that can infer the state of the whole population from a limited number of measures. We analyze the capability of deep neural networks to solve this challenging task. We base our proposed architecture on Graph Convolutional Neural Networks. As such, it can reason on the effect of the underlying social network structure, which is recognized as the main component in spreading an epidemic. The proposed architecture can reconstruct the entire state with accuracy above 70%, as proven by two scenarios modeled on the CoVid-19 pandemic. The first is a generic homogeneous population, and the second is a toy model of the Boston metropolitan area. Note that no retraining of the architecture is necessary when changing the model., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

Today's use of large-scale industrial robots is enabling extraordinary achievement on the assembly line, but these robots remain isolated from the humans on the factory floor because they are very powerful, and thus dangerous to be around. In contrast, the soft robotics research community has proposed soft robots that are safe for human environments. The current state of the art enables the creation of small-scale soft robotic devices. In this article we address the gap between small-scale soft robots and the need for human-sized safe robots by introducing a new soft robotic module and multiple human-scale robot configurations based on this module. We tackle large-scale soft robots by presenting a modular and reconfigurable soft robotic platform that can be used to build fully functional and untethered meter-scale soft robots. These findings indicate that a new wave of human-scale soft robots can be an alternative to classic rigid-bodied robots in tasks and environments where humans and machines can work side by side with capabilities that include, but are not limited to, autonomous legged locomotion and grasping., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work, Learning & Autonomous Control

The nature of continuum soft robots calls for novel perception solutions, which can provide information on the robot's shape while not substantially modifying their bodies' softness. One way to achieve this goal is to develop innovative and completely deformable sensors. However, these solutions tend to be less reliable than classic sensors for rigid robots. As an alternative, we consider here the use of monocular cameras. By admitting a small rigid component in our design, we can leverage well-established solutions from mobile robotics. We propose a shape sensing strategy that combines a SLAM algorithm with nonlinear optimization based on the robot's kinematic model. We prove the method's effectiveness in simulation and with experiments of a single-segment continuous soft robot with a camera mounted to the tip. We achieve mean relative translational errors below 9% simulations and experiments alike, and as low as 0.5% on average for some simulation conditions., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

The intrinsically underactuated and nonlinear nature of continuum soft robots makes the derivation of provably stable feedback control laws a challenging task. Most of the works so far circumvented the issue either by looking at coarse fully-actuated approximations of the dynamics or by imposing quasi-static assumptions. In this letter, we move a step in the direction of controlling generic soft robots taking explicitly into account their underactuation. A class of soft robots that have no direct elastic couplings between the dynamics of actuated and unactuated coordinates is identified. Considering the actuated variables as output, we prove that the system is minimum phase. We then propose regulators that implement different levels of model compensation. The stability of the associated closed-loop systems is formally proven by Lyapunov/LaSalle techniques, taking into account the nonlinear and underactuated dynamics. Simulation results are reported for two models of 2D and 3D soft robots., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

Adding elastic elements to the mechanical structure should enable robots to perform efficient oscillatory tasks. Still, even characterizing natural oscillations in nonlinear systems is a challenge in itself, which nonlinear modal theory promises to solve. Therein eigenmanifolds generalize eigenspaces to mechanical systems with non-Euclidean metrics and thus characterize families of oscillations that are autonomous evolutions of the robot. Eigenmanifolds likewise provide a framework for deriving feedback controllers to excite and sustain these oscillations. Nevertheless, these results have been so far essentially theoretical. They have been applied on relatively low dimensional systems and almost exclusively in simulation. We aim to bridge the theory to the real-world gap with the present work and show that we can excite nonlinear modes in complex systems. To this end, we propose control strategies that can simultaneously stabilize numerically evaluated eigenmanifolds and sustain oscillations in the presence of dissipation. We then focus on the KUKA iiwa with simulated parallel springs as an example of the highly nonlinear and articulated system. We calculate all the nonlinear modes of the system, and we use the proposed strategies to excite the associated natural oscillations., Accepted Author Manuscript, Learning & Autonomous Control

Nonlinear modes are a well investigated concept in dynamical systems theory, extending the celebrated modal analysis of linear mechanical systems to nonlinear ones. The present work moves a first step in the direction of combining control theory and nonlinear modal analysis towards the implementation of hyper-efficient oscillatory behaviors in mechanical systems with non-Euclidean metric. Rather than forcing a prescribed evolution, we first investigate the regular behaviors that can be autonomously expressed by the system, and then we design a controller that excites them. A first implementation of this concept is proposed, analyzed, and tested in simulation., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

Despite having proven successful in generating precise motions under dynamic conditions in highly deformable soft-bodied robots, model based techniques are also prone to robustness issues connected to the intrinsic uncertain nature of the dynamics of these systems. This letter aims at tackling this challenge, by extending the augmented rigid robot formulation to a stable representation of three dimensional motions of soft robots, under Piecewise Constant Curvature hypothesis. In turn, the equivalence between soft-bodied and rigid robots permits to derive effective adaptive controllers for soft-bodied robots, achieving perfect posture regulation under considerable errors in the knowledge of system parameters. The effectiveness of the proposed control design is demonstrated through extensive simulations., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

This letter discusses an extension of the famous PD regulator implementing point to point motions with prescribed exponential rates of convergence. This is achieved by deriving a novel global exponential stability result, dealing with mechanical systems evolving on uni-dimensional invariant manifolds of the configuration space. The construction of closed loop controllers enforcing the existence of such manifolds is then discussed. Explicit upper and lower bounds of convergence are provided, and connected to the gains of the closed loop controller. Simulations are carried out, assessing the effectiveness of the controller and the tightness of the exponential bounds., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

Shape estimation of soft robotic systems is challenging due to the range of deformations that can be achieved, and the limited availability of physically compatible sensors. We propose a method of reconstruction using Inertial Measurement Units (IMUs), which are mounted on segments of a deformable manipulator. This approach utilizes the piecewise constant curvature model in combination with the quaternion data from IMUs to allow for accuracy reconstruction and closed-loop control. A key strength of this approach is that it is hardware agnostic, and could be used on any soft structure to provide pose reconstruction and controllability. We explore this approach experimentally on a growing, extendable 3D printed continuum body structure, demonstrating that high accuracy reconstruction that can be achieved., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

Artificial cilia are a prominent example of physical intelligence. Their mechanical properties are often designed so to achieve desired motions in response to very simple actuation patterns. Yet, variability in the mechanical properties are inherent in these systems. This may critically disrupt the input-output relation, resulting in a final behavior completely different from the desired one. In this Communication we investigate the possibility of designing a robotic brain that helps the cilium to maintain its physical intelligence. We achieve that by closing a model-based control loop which tracks the position of the end effector while compensating for drag forces. We propose experiments to characterize our model, and extensive simulations validating the results in different conditions. This work is intended as a proof of concept, which will be further expanded in future work., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

Thanks to their body elasticity, articulated soft robots promise to produce effective and robust oscillations with low energy consumption. This in turn is an important feature which can be exploited in the execution of many tasks, as for example locomotion. Yet, an established theory and general techniques allowing to excite and sustain these nonlinear oscillations are still lacking. A possible solution to this problem comes from nonlinear modal theory, which defines curved extensions of linear Eigenspaces called Eigenmanifolds. Stabilizing these surfaces is equivalent to exciting regular hyper-efficient oscillations in the robotic system. This paper proposes a first experimental validation of the Eigenmanifold stabilization technique. It also proposes a simple yet effective means of injecting energy into the system, so to sustain the oscillations in presence of damping. We consider as experimental setups a single robotic leg, and a full soft quadruped. Preliminary locomotion results are provided with both systems., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

The need for users’ safety and technology acceptability has incredibly increased with the deployment of co-bots physically interacting with humans in industrial settings, and for people assistance. A well-studied approach to meet these requirements is to ensure human-like robot motions and interactions. In this manuscript, we present a research approach that moves from the understanding of human movements and derives usefull guidelines for the planning of arm movements and the learning of skills for physical interaction of robots with the surrounding environment., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control

Actuators’ dynamics have been so far mostly neglected when devising feedback controllers for continuum soft robots since the problem under the direct actuation hypothesis is already quite hard to solve. Directly considering actuation would have made the challenge too complex. However, these effects are, in practice, far from being negligible. The present work focuses on model-based control of piston-driven pneumatically-actuated soft robots. We propose a model of the relationship between the robot’s state, the acting fluidic pressure, and the piston dynamics, which is agnostic to the chosen model for the soft system dynamics. We show that backstepping is applicable even if the feedback coupling of the outer on the inner subsystem is not linear. Thus, we introduce a general model-based control strategy based on backstepping for soft robots actuated by fluidic drive. As an example, we derive a specialized version for a robot with piecewise constant curvature., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Learning & Autonomous Control