Model-agnostic fluidic proprioception framework for state estimation and precise movement in soft musculoskeletal robots
Bibliographic record
Abstract
• Novel framework estimates soft actuator state under actuation and disturbance • Uses only internal pressure data; no external sensors are required • Enables position and compliance control in bioinspired joint systems • Supports efficient trajectory imitation using a data-driven approach • Eliminates need for direct measurement via soft computing estimation Inspired by biological musculoskeletal structures, soft robots can achieve adaptable, compliant motion beyond the capabilities of conventional rigid systems. However, accurately modeling and manipulating soft actuators in soft robots remains challenging due to their inherent imprecision, nonlinearity, hysteresis, and high computational demands/difficulties that only intensify when extended to joint-space. To address these issues, this study introduces a fluidic proprioceptive state estimator (FProSE), a model-agnostic, soft computing framework that combines volume input and internal pressure measurements to estimate real-time actuator states under external disturbances. Instead of relying on direct measurement through external force or position sensors, FProSE infers joint states through learned internal dynamics, simplifying hardware requirements while enabling robust closed-loop adjustment in both a 2D antagonistic joint and an anthropomorphic 3-DoF artificial shoulder. Experimental validation shows over 95% and 82% estimation accuracy of joint position in the respective platforms, along with the capacity to actively tune multi-axial stiffness from 0.029 Nm/deg to 0.049 Nm/deg. Moreover, FProSE facilitates high-accuracy robotic imitation (R²>0.9) by recording and replaying motion trajectories. This approach not only addresses longstanding challenges in manipulating soft hydraulic muscles but also unlocks a wide range of potential applications, from wearable robotics to surgical robotic systems, where safety, adaptability, and precise motion are paramount.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".