Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2403.04729

Stretchable Pneumatic Sleeve for Adaptable, Low-Displacement Anchoring in Exosuits

Katalin Schaffer·Ultan Fallon·Margaret M. Coad
View original source ↗Read source document ↗Export metadata ↓

Abstract

Despite recent advances in wearable technology, interfacing movement assistance devices with the human body remains challenging. We present a stretchable pneumatic sleeve that can anchor an exosuit actuator to the human arm with a low displacement of the actuator's mounting point relative to the body during operation. Our sleeve has the potential to serve as an adaptable attachment mechanism for exosuits, since it can adjust its pressure to only compress the arm as much as needed to transmit the applied exosuit forces without a large displacement. We discuss the design of our sleeve, which is made of fabric pneumatic artificial muscle (fPAM) actuators formed into bands. We quantify the performance of nine fPAM bands of various lengths and widths, as well as three sleeves (an fPAM sleeve, a series pouch motor (SPM) sleeve as in previous literature, and an off the shelf hook and loop sleeve), through the measurement of the compressing force as a function of pressure and the localized pulling force that can be resisted as a function of both pressure and mounting point displacement. Our experimental results show that fPAM bands with smaller resting length and/or larger resting width produce higher forces. Also, when inflated, an fPAM sleeve that has equivalent dimensions to the SPM sleeve while fully stretched has similar performance to the SPM sleeve. While inflated, both pneumatic sleeves decrease the mounting point displacement compared to the hook and loop sleeve. Compared to the SPM sleeve, the fPAM sleeve is able to hold larger internal pressure before bursting, increasing its possible force range. Also, when not inflated, the fPAM sleeve resists the pulling force well, indicating its ability to provide anchoring when not actuated.

Explore related subjects

cs.RO

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Katalin Schaffer, Ultan Fallon, Margaret M. Coad. 2024-03-07. Stretchable Pneumatic Sleeve for Adaptable, Low-Displacement Anchoring in Exosuits. https://doi.org/10.1109/robosoft60065.2024.10522018

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

IMLE-VLA: Fast Single-Step Action Generation for Vision-Language-Action Policies

Vision-language-action (VLA) policies leverage pretrained vision-language backbones to achieve strong cross-task generalization. A leading design couples this backbone with a dedicated continuous action head trained via diffusion or flow matching. However, such heads rely on iterative multi-step sampling, for example 10 Euler steps in $\pi_{0.5}$. This creates an inference bottleneck that produces stop-and-go movement in the robot and slower task completion. We introduce IMLE-VLA, which replaces the iterative action head with a single-step conditional generator trained via conditional Implicit Maximum Likelihood Estimation (cIMLE). The cIMLE objective promotes multimodal action coverage, avoiding the mode collapse of naive regression heads while eliminating multi-step sampling entirely. When IMLE-VLA is applied to $\pi_{0.5}$, it increases inference frequency 3.67x (55 Hz vs. 15 Hz), enabling up to 11x higher action throughput. On the 40-task LIBERO benchmark, IMLE-VLA achieves the highest average success rate (98.0%) among all baselines while leading in inference frequency. Under the test-time perturbations of LIBERO-plus, IMLE-VLA retains $\pi_{0.5}$'s robustness while other baselines degrade sharply, confirming that the cIMLE head preserves generalization. Real-world experiments on a Franka Emika Panda across four tasks demonstrate smoother motion (2.2x to 3.0x lower jerk) and faster task completion, with IMLE-VLA outperforming $\pi_{0.5}$ on every task and reducing average VLA inference time per episode by 3.9x to 6.6x. Videos and code are available at https://kianhk6.github.io/IMLE-VLA/

cs.RO↗
arXiv2026

ObstaDiff: Generalizable Diffusion Policy Learning via Obstacle-aware Representations

Imitation learning has achieved impressive results in robotic manipulation, yet most existing approaches assume clean backgrounds and lack explicit mechanisms for obstacle-aware motion generation. Extending such policies to cluttered, real-world scenes with unstructured obstacles remains a key generalization challenge. We present ObstaDiff, a decomposed diffusion-policy framework with a lightweight obstacle-aware visual encoder. ObstaDiff extracts a structured target-obstacle-background representation, enabling the downstream alignment policy to generate end-effector trajectories toward a target-centered bottleneck pose while reasoning about surrounding obstacles. We evaluate ObstaDiff on 61 real-robot greenhouse trials per method (366 executions in total). ObstaDiff achieves 75.41% average task success and 8.20% average obstacle collision rate, outperforming representative imitation-learning baselines and improving generalization in cluttered agricultural scenes.

cs.RO↗
arXiv2026

Testing Between the Test Cases: Proving End-to-End Steering in Conditions You Never Drove

AI-based automated vehicle testing is challenging because a model that passes every test condition can still fail in the real world. Formal verification offers a way to directly address this gap. On a simulated highway and an arterial road we trained two small end-to-end steering networks each in CARLA, one on clear conditions alone and one on clear, fog, night and low sun. All four models were driven against a 2.19 ft lane-departure budget. Without driving again, we used bound propagation, a formal method that reads the trained weights, to compute how far steering can drift at every disturbance strength between two captured images. One calculation covers more than a campaign could drive: on the arterial it spans 133 poses, where ten intensities each would be 10^133 combinations, in minutes on one GPU. Not only did formal verification find conditions that broke the clear-trained policy without simulation testing, it provided some preliminary evidence for potential failures between the test cases. Our overall conclusion is that formal verification is a viable complement to simulation, and could be adopted as a part of verification and validation for automated driving.

cs.RO↗