Beyond Semantic Classes: Online Physical Parameter Estimation via Embedding-Conditioned Gaussian Mixtures
Beyond Semantic Classes: Online Physical Parameter Estimation via Embedding-Conditioned Gaussian Mixtures
This research introduces a real-time estimator that replaces semantic class indexing with an interaction-grounded Gaussian-mixture posterior over latent physical parameters, conditioned on continuous visual embeddings.
The authors present a novel method for online physical parameter estimation using embedding-conditioned Gaussian mixtures, demonstrating improved controller adaptation in autonomous racing simulations with varying friction surfaces.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Environment
- SimulationOpen source S5
- Control
- Reported autonomousOpen source S5
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
esentation. Our experiments show that the estimator recovers multimodal physical beliefs, rejects unrelated interaction history, avoids spatial map discretization, and evaluates at controller rates. In a high-fidelity autonomous racing simulation with unknown low- and high-friction surface regions, the posterior enables the controller to adapt over repeated laps as interaction evidence accumulates, improving performa
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org