aiqbench analysis
This research applies history-conditioned flow matching to address uncertainty in tendon-driven continuum robots, leveraging motion and actuation histories for probabilistic dynamics prediction. The framework outperforms diffusion and variational autoencoder baselines by accurately capturing future joint configurations even under unobserved friction variations and actuation disturbances. While the application is robotics-specific, the core methodology represents a significant advancement in using generative AI models to handle complex mechanical uncertainties.
History-Conditioned Flow Matching for Probabilistic Dynamics of Tendon-Driven Continuum Robots
arXiv:2609.25658v1 Announce Type: new Abstract: Deterministic dynamics modeling of tendon-driven continuum robots remains challenging owing to uncertainties in material behavior, tendon transmission, friction, and contact. Measured joint configurations and nominal tendon commands do not fully characterize these internal mechanical factors, leaving uncertainty in the subsequent motion. We therefore develop a history-conditioned, physics-informed flow-matching framework for probabilistic dynamics prediction, using motion and actuation histories to predict the distribution of the next complete joint configuration. By recursively sampling next-step configurations under prescribed commands, the model predicts distributions of future whole-body motions. In simulation, scenario-specific models achieve five-second trajectory Energy Scores (lower is better) of 12.05 mm under internal friction variation and 9.29 mm under unobserved actuation disturbances. Relative to the conditional variational autoencoder and diffusion baselines, Flow attains lower Energy Scores and coverage closer to the nominal level in both scenarios. Ablations support history and structural conditioning in both scenarios. On the physical robot, predictions under two tendon-command profiles excluded from training capture the principal motion sequences, with five-second Energy Scores of 11.91 and 11.42 mm, lower than the compared baselines. The predicted-to-measured spread ratios are 1.65 and 1.22 (closer to 1 is better). These results support history-conditioned probabilistic dynamics prediction under incomplete mechanical observations.
Abstract:Deterministic dynamics modeling of tendon-driven continuum robots remains challenging owing to uncertainties in material behavior, tendon transmission, friction, and contact. Measured joint configurations and nominal tendon commands do not fully characterize these internal mechanical factors, leaving uncertainty in the subsequent motion. We therefore develop a history-conditioned, physics-informed flow-matching framework for probabilistic dynamics prediction, using motion and actuation histories to predict the distribution of the next complete joint configuration. By recursively sampling next-step configurations under prescribed commands, the model predicts distributions of future whole-body motions. In simulation, scenario-specific models achieve five-second trajectory Energy Scores (lower is better) of 12.05 mm under internal friction variation and 9.29 mm under unobserved actuation disturbances. Relative to the conditional variational autoencoder and diffusion baselines, Flow attains lower Energy Scores and coverage closer to the nominal level in both scenarios. Ablations support history and structural conditioning in both scenarios. On the physical robot, predictions under two tendon-command profiles excluded from training capture the principal motion sequences, with five-second Energy Scores of 11.91 and 11.42 mm, lower than the compared baselines. The predicted-to-measured spread ratios are 1.65 and 1.22 (closer to 1 is better). These results support history-conditioned probabilistic dynamics prediction under incomplete mechanical observations.
Robotics (cs.RO)
arXiv:2609.25658 [cs.RO]
(or arXiv:2609.25658v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.25658 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 291 words
Related coverage
OceanFlow: Coherent Flow Matching for Probabilistic Ocean Modeling
arXiv · Oct 15, 2026
Variational Streaming Flow: Probabilistic Forecasting in Physical Time
arXiv · Oct 2, 2026
Learning a Resolution-Consistent Jacobian Field for Bio-Inspired Rigid-Soft Finger
arXiv · Oct 2, 2026
Modeling Stochastic Conditional Dynamics from Sparse Observations via Kernel-Stabilized Flow Matching
arXiv · Jun 9, 2026