Josie Hughes

Amplitude tuning is an important strategy in animals employing traveling wave patterns, enhancing their adaptability to unstructured environments. This paper proposes, for the first time, an amplitude tuning method that leverages the compliance of a soft corkscrew by twisting its ends. An amplitude tunable traveling wave robot (ATWBot) is developed, consisting of a soft corkscrew housed in a high DOF cage and driven by only two servos. The soft corkscrew and cage are monolithically 3D-printed. ATWBot achieves a wide range of active amplitude tuning with passive compliance adaptation, and can extend its morphology to a coiled configuration, enabling clamping and rolling. A comprehensive model is built for the twisted soft corkscrew geometry, proving that the robot's speed is decoupled from amplitude variations during twisting. A genetic algorithm is used to optimize the soft corkscrew for achieving the fastest speed while matching the cage geometry. Experiments demonstrate that the combination of active amplitude tuning and passive body compliance enables the robot to adapt to unstructured terrains including slits, steps, gaps, converging tunnels, slopes, and swimming.

The shoulder is important for humanoid robots since it has a significant impact on the arm’s range of motion and its versatility. Therefore, research on the shoulder joint, which is known as the spherical joint or ball–socket joint, is ongoing to mimic its wide workspace and high control accuracy. In this article, we propose a shoulder joint with a unique tendon-routing method. This method combines straight actuation tendons, passive helical tendons, and springs, preventing joint dislocation even in extreme conditions and ensuring controllability in all positions. We can also adjust dislocation characteristics by changing the number of tendons and tendon-routing method. The passive spring connections impose inherent compliance and improve stability in harsh situations. The tendons imitate human ligament and muscle in order to achieve structural and functional similarity to a human shoulder. The proposed joint has a $\pm$ 99.87$^{\circ }$ workspace with respect to roll and pitch rotation and withstands high impact with compliance. It has key advantages including the wide range of motion, diverse dislocation map, lightweight, and similarities with human shoulder motion and structure.

Robotics education can inspire and enhance STEM learning by covering interdisciplinary topics such as mathematics, physics, and engineering. However, traditional robotics platforms often face barriers to accessibility, as they require costly resources and specialized facilities. Soft robotics offers a promising alternative due to its low-cost, accessible materials and the potential to teach concepts of physical intelligence and materials science. We propose a hybrid educational toolkit consisting of a soft balloon robot paired with a physics-based simulator, enabling users to explore control and morphology in both virtual and physical contexts. We demonstrate the sim2real match between the robot and simulator, and the capacity to use both in a hybrid modality. This approach combines the advantages of simulation for rapid iteration with hands-on experimentation, providing an engaging and scalable platform for STEM education. To evaluate the pedagogical impact of this hybrid approach, we conducted user studies comparing learning outcomes across simulation-only, hardware-only, and hybrid interaction conditions. Our results indicate that the hybrid modality enhances users’ exploration of design parameters and comprehension of robotic system principles.

Soft continuum robots possess inherent compliance and ensure safe interactions. Whilst advantageous, their high degrees of freedom pose significant challenges for estimating the robot's configuration and sensing external contacts. Existing analytical methods rely on finite state-representations that do not accurately capture the complex deformations in these systems. Learning-based approaches have shown promise, as they do not require any prior assumptions about the state representation; however, there are still challenges in extending them to handle external contacts. To address these challenges, this study proposes a novel perception framework for soft robotic arms by using onboard sensor data and generative models to develop image-based perception systems capable of reconstructing the arm's state, even under external contact. Our approach features an automated data preprocessing pipeline that isolates the robot from the environmental background, enabling the training of robust perception models. It then utilizes onboard IMU data and actuation commands to generate a high-dimensional visual representation of the robot's state, while also detecting contact locations with high accuracy.

Teleoperation allows for control of an anthropomorphic robot hand by leveraging the human ability to perform complex manipulation tasks. However, the mismatch between the human and robot motions affects the intuitiveness and performance of teleoperation tasks. We propose a hybrid gesture-based mapping method, where a classifier first identifies a gesture from a predefined discrete set, and then a regression model determines the continuous gesture motion progression. The discrete nature of the classification allows for the robot to execute a predefined motion, matching the intention of the human, while the regression model allows for a continuous and thus smooth and intuitive experience. To benchmark the proposed method, we have also developed a baseline method that directly maps each human finger motion to the robot. We systematically evaluate the two methods by varying the operator to include those with varying experience levels and hand sizes, introducing signal delay of zero or one second, and testing across 20 object geometries. The proposed method outperforms the baseline through a 29% decrease in average grasping time for an expert (with and without a signal delay), an 34% increase in success rate, and a 64% increase in system usability scale (SUS) scores for novice users.

Bio‐hybrid robots utilize living organisms for robot design, however, their use of living bodies makes maintenance, control, and fabrication of robot challenging. As an alternative, exoskeletons stand out for retaining mobility after the organism's death, making them an accessible candidate. In particular, crustacean exoskeletons, often discarded as food waste, provide both structural strength and flexibility from their segmented rigid shell. By repurposing dead animals' part from bio‐waste, a sustainable cyclic design process is proposed in which materials can be recycled and adapted for new tasks after a robot's lifespan. In this paper, a bio‐hybrid robot design using the langoustine abdominal exoskeleton as a bending actuator is introduced. Through integration with synthetic components, augmented exoskeletons can generate diverse, fast, and robust motions with extended operational lifetimes. Three robotic applications are demonstrated using a 3 g exoskeleton capable of supporting a 680 g payload: a manipulator handling objects up to 500 g, fingers that grasp various objects and bend at speeds up to 8 Hz, and a swimming robot at speeds up to 11 cm s ⁻¹ . The method offers a sustainable robot design scheme and can be extended to diverse scales and functionalities by exploring a wide range of repurposable exoskeletons from bio‐waste.

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.

A safe, open-source, easily adaptable, laboratory sample transfer system that separates human and robot workflows and allows tasks to be performed on scientific instruments that are not ready for automation.