Robert K. Katzschmann

Jaehoon Kim, Lazaros Christoforidis, Michalis Papadakis et al. · eth-zurich, mit

Dexterous robotic hands require high-speed multimodal sensing across many degrees of freedom, yet existing readout architectures often impose trade-offs between sensor count, wiring complexity, and sampling bandwidth. This paper presents a scalable analog sensor readout architecture based on a serial-in parallel-out (SIPO) shift-register principle. The proposed architecture supports versatile integration of heterogeneous analog-output sensors, scalable expansion using only three signal lines between sensor modules, and fast, configurable sampling. We validate the approach on a tendon-driven robotic hand integrating 16 joint sensor modules and one four-channel tactile sensor module, enabling acquisition of 20 sensor channels at a full-scan rate of 1 kHz, with stable operation up to 1.5 kHz. Joint sensor characterization showed a maximum slope absolute percentage error (APE) of 0.446% and sub-degree estimation error, indicating that the proposed readout system does not significantly degrade sensing performance. For tactile sensing, LSTM-based models achieved an RMSE of 0.125 N for force estimation and 93.4% accuracy for five-class contact-location classification, and were deployed for real-time inference at 1 kHz. System-level experiments showed that the joint sensors provide more accurate feedback than motor-based estimation during interaction, while the tactile sensor enables responsive force estimation in contact. The proposed architecture offers a practical path toward fully sensorized robotic hands for dexterous manipulation.

Elvis Nava, Seijin Kobayashi, Yifei Yin et al. · eth-zurich, mit

We introduce meta-learning algorithms that perform zero-shot weight-space adaptation of neural network models to unseen tasks. Our methods repurpose the popular generative image synthesis techniques of natural language guidance and diffusion models to generate neural network weights adapted for tasks. We first train an unconditional generative hypernetwork model to produce neural network weights; then we train a second "guidance" model that, given a natural language task description, traverses the hypernetwork latent space to find high-performance task-adapted weights in a zero-shot manner. We explore two alternative approaches for latent space guidance: "HyperCLIP"-based classifier guidance and a conditional Hypernetwork Latent Diffusion Model ("HyperLDM"), which we show to benefit from the classifier-free guidance technique common in image generation. Finally, we demonstrate that our approaches outperform existing multi-task and meta-learning methods in a series of zero-shot learning experiments on our Meta-VQA dataset.

Erik Bauer, Elvis Nava, Robert K. Katzschmann · eth-zurich, mit

End-to-end learning is emerging as a powerful paradigm for robotic manipulation, but its effectiveness is limited by data scarcity and the heterogeneity of action spaces across robot embodiments. In particular, diverse action spaces across different end-effectors create barriers for cross-embodiment learning and skill transfer. We address this challenge through diffusion policies learned in a latent action space that unifies diverse end-effector actions. We first show that we can learn a semantically aligned latent action space for anthropomorphic robotic hands, a human hand, and a parallel jaw gripper using encoders trained with a contrastive loss. Second, we show that by using our proposed latent action space for co-training on manipulation data from different end-effectors, we can utilize a single policy for multi-robot control and obtain up to 25.3% improved manipulation success rates, indicating successful skill transfer despite a significant embodiment gap. Our approach using latent cross-embodiment policies presents a new method to unify different action spaces across embodiments, enabling efficient multi-robot control and data sharing across robot setups. This unified representation significantly reduces the need for extensive data collection for each new robot morphology, accelerates generalization across embodiments, and ultimately facilitates more scalable and efficient robotic learning.

Erik Bauer, Barnabas Gavin Cangan, Robert K. Katzschmann · eth-zurich, mit

In a future with autonomous robots, visual and spatial perception is of utmost importance for robotic systems. Particularly for aerial robotics, there are many applications where utilizing visual perception is necessary for any real-world scenarios. Robotic aerial grasping using drones promises fast pick-and-place solutions with a large increase in mobility over other robotic solutions. Utilizing Mask R-CNN scene segmentation (detectron2), we propose a vision-based system for autonomous rapid aerial grasping which does not rely on markers for object localization and does not require the appearance of the object to be previously known. Combining segmented images with spatial information from a depth camera, we generate a dense point cloud of the detected objects and perform geometry-based grasp planning to determine grasping points on the objects. In real-world experiments on a dynamically grasping aerial platform, we show that our system can replicate the performance of a motion capture system for object localization up to 94.5 % of the baseline grasping success rate. With our results, we show the first use of geometry-based grasping techniques with a flying platform and aim to increase the autonomy of existing aerial manipulation platforms, bringing them further towards real-world applications in warehouses and similar environments.

Amirhossein Kazemipour, Robert K. Katzschmann · eth-zurich, mit

Antagonistic artificial muscles can decouple joint torque and stiffness, but contact transients often degrade this independence. We present a unified real-time framework applicable across pneumatic, electrohydraulic, and dielectric elastomer artificial muscle families: a separable Padé force model with a minimal two-state dynamic wrapper, a cascaded inverse-dynamics controller in co-contraction/bias coordinates, and a bio-inspired depth-adaptive interaction policy that schedules stiffness based on penetration depth. The controller runs in under 1 ms per control tick and demonstrates independent torque and stiffness tracking, including a fixed-torque stiffness-step test that preserves torque regulation through stiffness transitions. In a coupled impedance contact protocol simulated across soft-to-rigid environments, comparing depth-adaptive stiffness to fixed-stiffness baselines reveals a shock/load versus stability tradeoff. These results provide a control-oriented foundation for musculoskeletal antagonistic robots to execute adaptive impedance behaviors in dynamic interactions.

Misato Sonoda, Ronan Hinchet, Amirhossein Kazemipour et al. · eth-zurich, mit

Robotic manipulation in unstructured environments requires end-effectors that combine high kinematic dexterity with physical compliance. While traditional rigid hands rely on complex external sensors for safe interaction, electrohydraulic actuators offer a promising alternative. This paper presents the design, control, and evaluation of a novel musculoskeletal robotic hand architecture powered entirely by remote Peano-HASEL actuators, specifically optimized for safe manipulation. By relocating the actuators to the forearm, we functionally isolate the grasping interface from electrical hazards while maintaining a slim, human-like profile. To address the inherently limited linear contraction of these soft actuators, we integrate a 1:2 pulley routing mechanism that mechanically amplifies tendon displacement. The resulting system prioritizes compliant interaction over high payload capacity, leveraging the intrinsic force-limiting characteristics of the actuators to provide a high level of inherent safety. Furthermore, this physical safety is augmented by the self-sensing nature of the HASEL actuators. By simply monitoring the operating current, we achieve real-time grasp detection and closed-loop contact-aware control without relying on external force transducers or encoders. Experimental results validate the system's dexterity and inherent safety, demonstrating the successful execution of various grasp taxonomies and the non-destructive grasping of highly fragile objects, such as a paper balloon. These findings highlight a significant step toward simplified, inherently compliant soft robotic manipulation.

Paul Leonard Wolff, Hugo Buurmeijer, Luis Pabon et al. · eth-zurich, mit

Continuum robots exhibit high-dimensional, nonlinear dynamics which are often coupled with their actuation mechanism. Spectral submanifold (SSM) reduction has emerged as a leading method for reducing high-dimensional nonlinear dynamical systems to low-dimensional invariant manifolds. Our proposed control-augmented SSMs (caSSMs) extend this methodology by explicitly incorporating control inputs into the state representation, enabling these models to capture nonlinear state-input couplings. Training these models relies solely on controlled decay trajectories of the actuator-augmented state, thereby removing the additional actuation-calibration step commonly needed by prior SSM-for-control methods. We learn a compact caSSM model for a tendon-driven trunk robot, enabling real-time control and reducing open-loop prediction error by 40% compared to existing methods. In closed-loop experiments with model predictive control (MPC), caSSM reduces tracking error by 52%, demonstrating improved performance against Koopman and SSM based MPC and practical deployability on hardware continuum robots.

Elham Amin Mansour, Hehui Zheng, Robert K. Katzschmann

The world around us is full of soft objects we perceive and deform with dexterous hand movements. For a robotic hand to control soft objects, it has to acquire online state feedback of the deforming object. While RGB-D cameras can collect occluded point clouds at a rate of 30Hz, this does not represent a continuously trackable object surface. Hence, in this work, we developed a method that takes as input a template mesh which is the mesh of an object in its non-deformed state and a deformed point cloud of the same object, and then shapes the template mesh such that it matches the deformed point cloud. The reconstruction of meshes from point clouds has long been studied in the field of Computer graphics under 3D reconstruction and 4D reconstruction, however, both lack the speed and generalizability needed for robotics applications. Our model is designed using a point cloud auto-encoder and a Real-NVP architecture. Our trained model can perform mesh reconstruction and tracking at a rate of 58Hz on a template mesh of 3000 vertices and a deformed point cloud of 5000 points and is generalizable to the deformations of six different object categories which are assumed to be made of soft material in our experiments (scissors, hammer, foam brick, cleanser bottle, orange, and dice). The object meshes are taken from the YCB benchmark dataset. An instance of a downstream application can be the control algorithm for a robotic hand that requires online feedback from the state of the manipulated object which would allow online grasp adaptation in a closed-loop manner. Furthermore, the tracking capacity of our method can help in the system identification of deforming objects in a marker-free approach. In future work, we will extend our trained model to generalize beyond six object categories and additionally to real-world deforming point clouds.

Senlan Yao, Chenyu Yang, Jaehoon Kim et al.

In-hand object manipulation is a fundamental yet challenging capability for dexterous robots. Despite significant progress in dexterous manipulation, existing approaches rely heavily on vision or tactile sensing to track object states, while joint sensing -- the most readily available modality on any robotic hand -- remains largely overlooked, particularly for tendon-driven hands. In this paper, we study how far joint sensing alone can go by asking: (i) whether motor encoders or direct joint sensing provides better proprioceptive feedback, (ii) how to extract environment information from joint measurements, and (iii) whether joint-only control can achieve competitive real-world performance without external perception. We present the Proprioceptive Transformer (PT), an exteroceptive-free approach for continuous cube rotation on a tendon-driven dexterous hand that uses only joint sensing feedback. A teacher policy is first trained via reinforcement learning with privileged object information, then distilled into PT, which operates solely on joint position and velocity histories. The Transformer architecture effectively extracts implicit object state information from temporal patterns in joint sensor readings. Experiments on the real ORCA hand show that our approach achieves 3.1x higher rotation speed than baselines. We also demonstrate that our PT achieves a 23.4% lower RMSE for cube position estimation than the MLP baseline, indicating superior extraction of exteroceptive information from proprioceptive sources.

Chenyu Yang, Denis Tarasov, Davide Liconti et al.

Real-world fine-tuning of dexterous manipulation policies remains challenging due to limited real-world interaction budgets and highly multimodal action distributions. Diffusion-based policies, while expressive, do not permit conservative likelihood-based updates during fine-tuning because action probabilities are intractable. In contrast, conventional Gaussian policies collapse under multimodality, particularly when actions are executed in chunks, and standard per-step critics fail to align with chunked execution, leading to poor credit assignment. We present SOFT-FLOW, a sample-efficient off-policy fine-tuning framework with normalizing flow (NF) to address these challenges. The normalizing flow policy yields exact likelihoods for multimodal action chunks, allowing conservative, stable policy updates through likelihood regularization and thereby improving sample efficiency. An action-chunked critic evaluates entire action sequences, aligning value estimation with the policy's temporal structure and improving long-horizon credit assignment. To our knowledge, this is the first demonstration of a likelihood-based, multimodal generative policy combined with chunk-level value learning on real robotic hardware. We evaluate SOFT-FLOW on two challenging dexterous manipulation tasks in the real world: cutting tape with scissors retrieved from a case, and in-hand cube rotation with a palm-down grasp -- both of which require precise, dexterous control over long horizons. On these tasks, SOFT-FLOW achieves stable, sample-efficient adaptation where standard methods struggle.

Hehui Zheng, Bhavya Sukhija, Chenhao Li et al.

Soft robots offer unmatched adaptability and safety in unstructured environments, yet their compliant, high-dimensional, and nonlinear dynamics make modeling for control notoriously difficult. Existing data-driven approaches often fail to generalize, constrained by narrowly focused task demonstrations or inefficient random exploration. We introduce SoftAE, an uncertainty-aware active exploration framework that autonomously learns task-agnostic and generalizable dynamics models of soft robotic systems. SoftAE employs probabilistic ensemble models to estimate epistemic uncertainty and actively guides exploration toward underrepresented regions of the state-action space, achieving efficient coverage of diverse behaviors without task-specific supervision. We evaluate SoftAE on three simulated soft robotic platforms -- a continuum arm, an articulated fish in fluid, and a musculoskeletal leg with hybrid actuation -- and on a pneumatically actuated continuum soft arm in the real world. Compared with random exploration and task-specific model-based reinforcement learning, SoftAE produces more accurate dynamics models, enables superior zero-shot control on unseen tasks, and maintains robustness under sensing noise, actuation delays, and nonlinear material effects. These results demonstrate that uncertainty-driven active exploration can yield scalable, reusable dynamics models across diverse soft robotic morphologies, representing a step toward more autonomous, adaptable, and data-efficient control in compliant robots.

Davide Liconti, Yuning Zhou, Yasunori Toshimitsu et al.

Dexterity is a central yet ambiguously defined concept in the design and evaluation of anthropomorphic robotic hands. In practice, the term is often used inconsistently, with different systems evaluated under disparate criteria, making meaningful comparisons across designs difficult. This highlights the need for a unified, performance-based definition of dexterity grounded in measurable outcomes rather than proxy metrics. In this work, we introduce POMDAR, a comprehensive dexterity benchmark that formalizes dexterity as task performance across a structured set of manipulation and grasping motions. The benchmark was systematically derived from established taxonomies in human motor control. It is implemented in both real-world and simulation and includes four manipulation configurations: vertical and horizontal configurations, continuous rotation, and pure grasping. The task designs contain mechanical scaffolding to constrain task motion, suppress compensatory strategies, and enable metrics to be measured unambiguously. We define a quantitative scoring metric combining task correctness and execution speed, effectively measuring dexterity as throughput. This enables objective, reproducible, and interpretable evaluation across different hand designs. POMDAR provides an open-source, standardized, and taxonomy-grounded benchmark for consistent comparison and evaluation of anthropomorphic robot hands to facilitate a systematic advancement of dexterous manipulation platforms. CAD, simulation files, and evaluation videos are publicly available at https://srl-ethz.github.io/POMDAR/.

Alexey Gavryushin, Xi Wang, Robert J. S. Malate et al. · eth-zurich, mit

Large-scale egocentric video datasets capture diverse human activities across a wide range of scenarios, offering rich and detailed insights into how humans interact with objects, especially those that require fine-grained dexterous control. Such complex, dexterous skills with precise controls are crucial for many robotic manipulation tasks, yet are often insufficiently addressed by traditional data-driven approaches to robotic manipulation. To address this gap, we leverage manipulation priors learned from large-scale egocentric video datasets to improve policy learning for dexterous robotic manipulation tasks. We present MAPLE, a novel method for dexterous robotic manipulation that exploits rich manipulation priors to enable efficient policy learning and better performance on diverse, complex manipulation tasks. Specifically, we predict hand-object contact points and detailed hand poses at the moment of hand-object contact and use the learned features to train policies for downstream manipulation tasks. Experimental results demonstrate the effectiveness of MAPLE across existing simulation benchmarks, as well as a newly designed set of challenging simulation tasks, which require fine-grained object control and complex dexterous skills. The benefits of MAPLE are further highlighted in real-world experiments using a dexterous robotic hand, whereas simultaneous evaluation across both simulation and real-world experiments has remained underexplored in prior work.

Vittorio Candiello, Manuel Mekkattu, Mike Y. Michelis et al.

Soft robots achieve functionality through tight coupling among geometry, material composition, and actuation. As a result, effective design optimization requires these three aspects to be considered jointly rather than in isolation. This coupling is computationally challenging: nonlinear large-deformation mechanics increase simulation cost, while contact, collision handling, and non-smooth state transitions limit the applicability of standard gradient-based approaches. We introduce a smooth, low-dimensional design embedding for soft robots that unifies shape morphing, multi-material distribution, and actuation within a single structured parameter space. Shape variation is modeled through continuous deformation maps of a reference geometry, while material properties are encoded as spatial fields. Both are constructed from shared basis functions. This representation enables expressive co-design while drastically reducing the dimensionality of the search space. In our experiments, we show that design expressiveness increases with the number of basis functions, unlike comparable neural network encodings whose representational capacity does not scale predictably with parameter count. We further show that joint co-optimization of shape, material, and actuation using our unified embedding consistently outperforms sequential strategies. All experiments are performed independently of the underlying simulator, confirming compatibility with black-box simulation pipelines. Across multiple dynamic tasks, the proposed embedding surpasses neural network and voxel-based baseline parameterizations while using significantly fewer design parameters. Together, these findings demonstrate that structuring the design space itself enables efficient co-design of soft robots.

Levi Lingsch, Mike Y. Michelis, Emmanuel de Bezenac et al.

The computational efficiency of many neural operators, widely used for learning solutions of PDEs, relies on the fast Fourier transform (FFT) for performing spectral computations. As the FFT is limited to equispaced (rectangular) grids, this limits the efficiency of such neural operators when applied to problems where the input and output functions need to be processed on general non-equispaced point distributions. Leveraging the observation that a limited set of Fourier (Spectral) modes suffice to provide the required expressivity of a neural operator, we propose a simple method, based on the efficient direct evaluation of the underlying spectral transformation, to extend neural operators to arbitrary domains. An efficient implementation* of such direct spectral evaluations is coupled with existing neural operator models to allow the processing of data on arbitrary non-equispaced distributions of points. With extensive empirical evaluation, we demonstrate that the proposed method allows us to extend neural operators to arbitrary point distributions with significant gains in training speed over baselines while retaining or improving the accuracy of Fourier neural operators (FNOs) and related neural operators.

Mike Y. Michelis, Robert K. Katzschmann

Enhancing neural networks with knowledge of physical equations has become an efficient way of solving various physics problems, from fluid flow to electromagnetism. Graph neural networks show promise in accurately representing irregularly meshed objects and learning their dynamics, but have so far required supervision through large datasets. In this work, we represent meshes naturally as graphs, process these using Graph Networks, and formulate our physics-based loss to provide an unsupervised learning framework for partial differential equations (PDE). We quantitatively compare our results to a classical numerical PDE solver, and show that our computationally efficient approach can be used as an interactive PDE solver that is adjusting boundary conditions in real-time and remains sufficiently close to the baseline solution. Our inherently differentiable framework will enable the application of PDE solvers in interactive settings, such as model-based control of soft-body deformations, or in gradient-based optimization methods that require a fully differentiable pipeline.

Elvis Nava, John Z. Zhang, Mike Y. Michelis et al.

Aquatic locomotion is a classic fluid-structure interaction (FSI) problem of interest to biologists and engineers. Solving the fully coupled FSI equations for incompressible Navier-Stokes and finite elasticity is computationally expensive. Optimizing robotic swimmer design within such a system generally involves cumbersome, gradient-free procedures on top of the already costly simulation. To address this challenge we present a novel, fully differentiable hybrid approach to FSI that combines a 2D direct numerical simulation for the deformable solid structure of the swimmer and a physics-constrained neural network surrogate to capture hydrodynamic effects of the fluid. For the deformable solid simulation of the swimmer's body, we use state-of-the-art techniques from the field of computer graphics to speed up the finite-element method (FEM). For the fluid simulation, we use a U-Net architecture trained with a physics-based loss function to predict the flow field at each time step. The pressure and velocity field outputs from the neural network are sampled around the boundary of our swimmer using an immersed boundary method (IBM) to compute its swimming motion accurately and efficiently. We demonstrate the computational efficiency and differentiability of our hybrid simulator on a 2D carangiform swimmer. Due to differentiability, the simulator can be used for computational design of controls for soft bodies immersed in fluids via direct gradient-based optimization.

Yu Zhang, Robert K. Katzschmann

Research on the co-optimization of soft robotic design and control requires rapid means for real-world validation. Existing creation pipelines do not allow for the swift prototyping of soft robots to quickly test various design configurations and control policies. This work proposes a pipeline for rapid iterative design and fabrication of a miniaturized modular silicone-elastomer-based robotic fish. The modular design allows simple and rapid iterations of robotic fishes with varying configurations to assist current research efforts on the development of design optimization methods. The proposed robotic fish can serve as a standardized test platform on which performance metrics such as thrust and range of motion can be evaluated. We further show the design of an underwater evaluation setup capable of measuring input pressure, tail deformation, and thrust. Multiple robotic fish prototypes with varying stiffness and internal pneumatic chamber configurations are fabricated and experimentally evaluated. The presented flexible modular design principle for the robot and its evaluation platform unlocks the possibilities of more efficient soft robotic fish and will benefit research on design optimization and underwater exploration in the future.

Oliver Fischer, Yasunori Toshimitsu, Amirhossein Kazemipour et al.

Dynamic motions are a key feature of robotic arms, enabling them to perform tasks quickly and efficiently. Soft continuum manipulators do not currently consider dynamic parameters when operating in task space. This shortcoming makes existing soft robots slow and limits their ability to deal with external forces, especially during object manipulation. We address this issue by using dynamic operational space control. Our control approach takes into account the dynamic parameters of the 3D continuum arm and introduces new models that enable multi-segment soft manipulators to operate smoothly in task space. Advanced control methods, previously afforded only to rigid robots, are now adapted to soft robots; for example, potential field avoidance was previously only shown for rigid robots and is now extended to soft robots. Using our approach, a soft manipulator can now achieve a variety of tasks that were previously not possible: we evaluate the manipulator's performance in closed-loop controlled experiments such as pick-and-place, obstacle avoidance, throwing objects using an attached soft gripper, and deliberately applying forces to a surface by drawing with a grasped piece of chalk. Besides the newly enabled skills, our approach improves tracking accuracy by 59% and increases speed by a factor of 19.3 compared to state of the art for task space control. With these newfound abilities, soft robots can start to challenge rigid robots in the field of manipulation. Our inherently safe and compliant soft robot moves the future of robotic manipulation towards a cageless setup where humans and robots work in parallel.

John Z. Zhang, Yu Zhang, Pingchuan Ma et al.

Accurate simulation of soft mechanisms under dynamic actuation is critical for the design of soft robots. We address this gap with our differentiable simulation tool by learning the material parameters of our soft robotic fish. On the example of a soft robotic fish, we demonstrate an experimentally-verified, fast optimization pipeline for learning the material parameters from quasi-static data via differentiable simulation and apply it to the prediction of dynamic performance. Our method identifies physically plausible Young's moduli for various soft silicone elastomers and stiff acetal copolymers used in creation of our three different robotic fish tail designs. We show that our method is compatible with varying internal geometry of the actuators, such as the number of hollow cavities. Our framework allows high fidelity prediction of dynamic behavior for composite bi-morph bending structures in real hardware to millimeter-accuracy and within 3 percent error normalized to actuator length. We provide a differentiable and robust estimate of the thrust force using a neural network thrust predictor; this estimate allows for accurate modeling of our experimental setup measuring bollard pull. This work presents a prototypical hardware and simulation problem solved using our differentiable framework; the framework can be applied to higher dimensional parameter inference, learning control policies, and computational design due to its differentiable character.

Amirhossein Kazemipour, Oliver Fischer, Yasunori Toshimitsu et al.

Soft robots are made of compliant materials and perform tasks that are challenging for rigid robots. However, their continuum nature makes it difficult to develop model-based control strategies. This work presents a robust model-based control scheme for soft continuum robots. Our dynamic model is based on the Euler-Lagrange approach, but it uses a more accurate description of the robot's inertia and does not include oversimplified assumptions. Based on this model, we introduce an adaptive sliding mode control scheme, which is robust against model parameter uncertainties and unknown input disturbances. We perform a series of experiments with a physical soft continuum arm to evaluate the effectiveness of our controller at tracking task-space trajectory under different payloads. The tracking performance of the controller is around 38\% more accurate than that of a state-of-the-art controller, i.e., the inverse dynamics method. Moreover, the proposed model-based control design is flexible and can be generalized to any continuum robotic arm with an arbitrary number of segments. With this control strategy, soft robotic object manipulation can become more accurate while remaining robust to disturbances.

Pingchuan Ma, Tao Du, John Z. Zhang et al.

The computational design of soft underwater swimmers is challenging because of the high degrees of freedom in soft-body modeling. In this paper, we present a differentiable pipeline for co-designing a soft swimmer's geometry and controller. Our pipeline unlocks gradient-based algorithms for discovering novel swimmer designs more efficiently than traditional gradient-free solutions. We propose Wasserstein barycenters as a basis for the geometric design of soft underwater swimmers since it is differentiable and can naturally interpolate between bio-inspired base shapes via optimal transport. By combining this design space with differentiable simulation and control, we can efficiently optimize a soft underwater swimmer's performance with fewer simulations than baseline methods. We demonstrate the efficacy of our method on various design problems such as fast, stable, and energy-efficient swimming and demonstrate applicability to multi-objective design.