analiza aiqbench
This research proposes using Neural ODEs to estimate geodesics on Riemannian manifolds, addressing the computational overhead of traditional methods for robot motion planning involving orientation. By encoding both position and orientation data within curved spaces, the framework aims to generate more natural and complex robotic movements compared to standard Euclidean space approaches. The study provides initial simulation insights and outlines future challenges for deploying these geodesic computations in real-world robotic tasks.
Learning from Demonstrations over Riemannian Manifolds using Neural ODEs: An Extended Abstract
arXiv:2606.05422v1 Announce Type: new Abstract: Learning from demonstratins (LfD) is usually performed over Euclidean spaces, while the robot state, e.g. orientation, naturally evolves over curved spaces. Therefore, to ensure natural, complex motion generation, we investigate learning from demonstrations over Riemannian manifolds that are capable of encoding both position and orientation data. Here, geodesic paths provide for natural motion between two arbitrary points within the manifold. We propose to numerically estimate geodesics via neural ordinary differential equations, mitigating large computational overhead of existing approaches. Finally, these geodesics can be decoded back into the original task space before deploying on the robot. In this extended abstract, we discuss the architecture of our framework, provide some initial insights from our simulation experiments, including comparison to other geodesic computation mechanisms, and discuss the challenges and prospects for future work.
Abstract:Learning from demonstratins (LfD) is usually performed over Euclidean spaces, while the robot state, e.g. orientation, naturally evolves over curved spaces. Therefore, to ensure natural, complex motion generation, we investigate learning from demonstrations over Riemannian manifolds that are capable of encoding both position and orientation data. Here, geodesic paths provide for natural motion between two arbitrary points within the manifold. We propose to numerically estimate geodesics via neural ordinary differential equations, mitigating large computational overhead of existing approaches. Finally, these geodesics can be decoded back into the original task space before deploying on the robot. In this extended abstract, we discuss the architecture of our framework, provide some initial insights from our simulation experiments, including comparison to other geodesic computation mechanisms, and discuss the challenges and prospects for future work.
Robotics (cs.RO)
arXiv:2606.05422 [cs.RO]
(or arXiv:2606.05422v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.05422 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.
Text integral sub licența deschisă a publicației · 223 cuvinte
Subiecte conexe
Asymmetric Friction in Geometric Locomotion
arXiv · 16 iun. 2026
Sparse Gaussian-Mixture-Model Q-Functions via Hadamard Overparametrization for Online Reinforcement Learning
arXiv · 28 iul. 2026
How Entanglement Reshapes the Geometry of Quantum Differential Privacy
arXiv · 27 iul. 2026
The Timing Dependencies of Trust: Speed, Accuracy, and cBCI Neuro-Decoupling in Human-AI Teams
arXiv · 4 sept. 2026