Josie Hughes

Fang Nan, Hao Ma, Qinghua Guan et al.

We present an online model-based reinforcement learning algorithm suitable for controlling complex robotic systems directly in the real world. Unlike prevailing sim-to-real pipelines that rely on extensive offline simulation and model-free policy optimization, our method builds a dynamics model from real-time interaction data and performs policy updates guided by the learned dynamics model. This efficient model-based reinforcement learning scheme significantly reduces the number of samples to train control policies, enabling direct training on real-world rollout data. This significantly reduces the influence of bias in the simulated data, and facilitates the search for high-performance control policies. We adopt online optimization analysis to derive sublinear regret bounds under stochastic online optimization assumptions, providing formal guarantees on performance improvement as more interaction data are collected. Experimental evaluations were performed on a hydraulic excavator arm and a soft robot arm, where the algorithm demonstrates strong sample efficiency compared to model-free reinforcement learning methods, reaching comparable performance within hours. Robust adaptation to shifting dynamics was also observed when the payload condition was randomized. Our approach paves the way toward efficient and reliable on-robot learning for a broad class of challenging control tasks.

Qiyuan Fu, Sudong Lee, Andrea Grillo et al.

Robots benefit from sensory information to coordinate body movement, gain robustness against perturbations, and transit between different modes to adapt to various terrains. However, few amphibious robots can sense interactions with both terrestrial and aquatic environments. In this paper, we present a solution that uses Hall-effect sensors to sense foot contact forces and lateral hydrodynamic forces on a salamander-inspired amphibious robot. With two bus lines, the robot can simultaneously acquire this exteroceptive information at more than 500 Hz and proprioceptive information, such as joint positions and loads, at 100 Hz. The Hall-effect sensors used are compact, making them suitable for embedding in multiple positions within a robot, and exhibit high sensitivity to small forces. Moreover, because the sensor can be positioned separately from the measured object, waterproofing can be implemented with relative ease. Our tests demonstrate the robot's capabilities in traversing amphibious environments and its potential in using feedback control for more complex locomotion tasks.

Andrew Wilhelm, Josie Hughes

Robot swarms offer inherent robustness and the capacity to execute complex, collaborative tasks surpassing the capabilities of single-agent systems. Co-designing these systems is critical, as marginal improvements in individual performance or unit cost compound significantly at scale. However, under traditional frameworks, this scale renders co-design intractable due to exponentially large, non-intuitive design spaces. To address this, we propose SwarmCoDe, a novel Collaborative Co-Evolutionary Algorithm (CCEA) that utilizes dynamic speciation to automatically scale swarm heterogeneity to match task complexity. Inspired by biological signaling mechanisms for inter-species cooperation, the algorithm uses evolved genetic tags and a selectivity gene to facilitate the emergent identification of symbiotically beneficial partners without predefined species boundaries. Additionally, an evolved dominance gene dictates the relative swarm composition, decoupling the physical swarm size from the evolutionary population. We apply SwarmCoDe to simultaneously optimize task planning and hardware morphology under fabrication budgets, successfully evolving specialized swarms of up to 200 agents -- four times the size of the evolutionary population. This framework provides a scalable, computationally viable pathway for the holistic co-design of large-scale, heterogeneous robot swarms.

Kevin Qiu, Kyle Walker, Mike Y. Michelis et al.

We present Swim2Real, a pipeline that calibrates a 16-parameter robotic fish simulator from swimming videos using vision-language model (VLM) feedback, requiring no hand-designed search stages. Calibrating soft aquatic robots is particularly challenging because nonlinear fluid-structure coupling makes the parameter landscape chaotic, simplified fluid models introduce a persistent sim-to-real gap, and controlled aquatic experiments are difficult to reproduce. Prior work on this platform required three manually tailored stages to handle this complexity. The VLM compares simulated and real videos and proposes parameter updates. A backtracking line search then validates each step size, tripling the accept rate from 14% to 42% by recovering proposals where the direction is correct but the magnitude is too large. Swim2Real calibrates all 16 parameters simultaneously, most closely matching real fish velocities across all motor frequencies (MAE = 7.4 mm/s, 43% lower than the next-best method), with zero outlier seeds across five runs. Motor commands from the trained policy transfer to the physical fish at 50 Hz, completing the pipeline from swimming video to real-world deployment. Downstream RL policies swim 12% farther than those from BayesOpt-calibrated simulators and 90% farther than CMA-ES. These results demonstrate that VLM-guided calibration can close the sim-to-real gap for aquatic robots directly from video, enabling zero-shot RL transfer to physical swimmers without manual system identification, a step toward automated, general-purpose simulator tuning for underwater robotics.

Kevin Qiu, Yu Zhang, Marek Cygan et al.

Calibrating a robot simulator's physics parameters (friction, damping, material stiffness) to match real hardware is often done by hand or with black-box optimizers that reduce error but cannot explain which physical discrepancies drive the error. When sensing is limited to external cameras, the problem is further compounded by perception noise and the absence of direct force or state measurements. We present Vid2Sid, a video-driven system identification pipeline that couples foundation-model perception with a VLM-in-the-loop optimizer that analyzes paired sim-real videos, diagnoses concrete mismatches, and proposes physics parameter updates with natural language rationales. We evaluate our approach on a tendon-actuated finger (rigid-body dynamics in MuJoCo) and a deformable continuum tentacle (soft-body dynamics in PyElastica). On sim2real holdout controls unseen during training, Vid2Sid achieves the best average rank across all settings, matching or exceeding black-box optimizers while uniquely providing interpretable reasoning at each iteration. Sim2sim validation confirms that Vid2Sid recovers ground-truth parameters most accurately (mean relative error under 13\% vs. 28--98\%), and ablation analysis reveals three calibration regimes. VLM-guided optimization excels when perception is clean and the simulator is expressive, while model-class limitations bound performance in more challenging settings.

Cheng Pan, Kai Junge, Josie Hughes

To advance autonomous dexterous manipulation, we propose a hybrid control method that combines the relative advantages of a fine-tuned Vision-Language-Action (VLA) model and diffusion models. The VLA model provides language commanded high-level planning, which is highly generalizable, while the diffusion model handles low-level interactions which offers the precision and robustness required for specific objects and environments. By incorporating a switching signal into the training-data, we enable event based transitions between these two models for a pick-and-place task where the target object and placement location is commanded through language. This approach is deployed on our anthropomorphic ADAPT Hand 2, a 13DoF robotic hand, which incorporates compliance through series elastic actuation allowing for resilience for any interactions: showing the first use of a multi-fingered hand controlled with a VLA model. We demonstrate this model switching approach results in a over 80\% success rate compared to under 40\% when only using a VLA model, enabled by accurate near-object arm motion by the VLA model and a multi-modal grasping motion with error recovery abilities from the diffusion model.

Cheng Pan, Hung Hon Cheng, Josie Hughes

Teleoperated robotic manipulators enable the collection of demonstration data, which can be used to train control policies through imitation learning. However, such methods can require significant amounts of training data to develop robust policies or adapt them to new and unseen tasks. While expert feedback can significantly enhance policy performance, providing continuous feedback can be cognitively demanding and time-consuming for experts. To address this challenge, we propose to use a cable-driven teleoperation system which can provide spatial corrections with 6 degree of freedom to the trajectories generated by a policy model. Specifically, we propose a correction method termed Decaying Relative Correction (DRC) which is based upon the spatial offset vector provided by the expert and exists temporarily, and which reduces the intervention steps required by an expert. Our results demonstrate that DRC reduces the required expert intervention rate by 30\% compared to a standard absolute corrective method. Furthermore, we show that integrating DRC within an online imitation learning framework rapidly increases the success rate of manipulation tasks such as raspberry harvesting and cloth wiping.

Haochen Su, Cristian Meo, Francesco Stella et al.

Robotic systems are increasingly expected to operate in human-centered, unstructured environments where safety, adaptability, and generalization are essential. Vision-Language-Action (VLA) models have been proposed as a language guided generalized control framework for real robots. However, their deployment has been limited to conventional serial link manipulators. Coupled by their rigidity and unpredictability of learning based control, the ability to safely interact with the environment is missing yet critical. In this work, we present the deployment of a VLA model on a soft continuum manipulator to demonstrate autonomous safe human-robot interaction. We present a structured finetuning and deployment pipeline evaluating two state-of-the-art VLA models (OpenVLA-OFT and $π_0$) across representative manipulation tasks, and show while out-of-the-box policies fail due to embodiment mismatch, through targeted finetuning the soft robot performs equally to the rigid counterpart. Our findings highlight the necessity of finetuning for bridging embodiment gaps, and demonstrate that coupling VLA models with soft robots enables safe and flexible embodied AI in human-shared environments.

Maximilian Stölzle, T. Konstantin Rusch, Zach J. Patterson et al. · eth-zurich

Learning from demonstration provides a sample-efficient approach to acquiring complex behaviors, enabling robots to move robustly, compliantly, and with fluidity. In this context, Dynamic Motion Primitives offer built - in stability and robustness to disturbances but often struggle to capture complex periodic behaviors. Moreover, they are limited in their ability to interpolate between different tasks. These shortcomings substantially narrow their applicability, excluding a wide class of practically meaningful tasks such as locomotion and rhythmic tool use. In this work, we introduce Orbitally Stable Motion Primitives (OSMPs) - a framework that combines a learned diffeomorphic encoder with a supercritical Hopf bifurcation in latent space, enabling the accurate acquisition of periodic motions from demonstrations while ensuring formal guarantees of orbital stability and transverse contraction. Furthermore, by conditioning the bijective encoder on the task, we enable a single learned policy to represent multiple motion objectives, yielding consistent zero-shot generalization to unseen motion objectives within the training distribution. We validate the proposed approach through extensive simulation and real-world experiments across a diverse range of robotic platforms - from collaborative arms and soft manipulators to a bio-inspired rigid-soft turtle robot - demonstrating its versatility and effectiveness in consistently outperforming state-of-the-art baselines such as diffusion policies, among others.

Toby Howison, Simon Hauser, Josie Hughes et al.

In this review we introduce the framework of reality-assisted evolution to summarize a growing trend towards combining model-based and model-free approaches to improve the design of physically embodied soft robots. In silico, data-driven models build, adapt and improve representations of the target system using real-world experimental data. By simulating huge numbers of virtual robots using these data-driven models, optimization algorithms can illuminate multiple design candidates for transference to the real world. In reality, large-scale physical experimentation facilitates the fabrication, testing and analysis of multiple candidate designs. Automated assembly and reconfigurable modular systems enable significantly higher numbers of real-world design evaluations than previously possible. Large volumes of ground-truth data gathered via physical experimentation can be returned to the virtual environment to improve data-driven models and guide optimization. Grounding the design process in physical experimentation ensures the complexity of virtual robot designs does not outpace the model limitations or available fabrication technologies. We outline key developments in the design of physically embodied soft robots under the framework of reality-assisted evolution.