Event
Proposing a Cross-Coupled and Operating-Condition-Dependent Dynamics Learning Framework for Aerial Manipulation
1 reports · 1 sources
Rishabh Dev Yadav and other researchers proposed a structured encoder-decoder framework for residual dynamics modeling and online adaptation of aerial manipulation platforms: a nonlinear history encoder captures the temporal and cross-coupled residual dynamics of the platform and the robotic arm, and a linear latent-space decoder supports rapid adaptation during deployment. The framework's linear-in-parameters structure enables closed-form Bayesian updates and integration with real-time model predictive control (MPC). Experiments on a real aerial manipulation platform show improved residual prediction accuracy, rapid adaptation after dynamics changes, and reduced MPC tracking error under payload variation conditions.
Report timeline
- Learning Cross-Coupled and Regime-Dependent Dynamics for Aerial Manipulation
A study proposes a structured encoder-decoder framework in which a nonlinear history encoder captures the temporal and cross-coupled residual dynamics of an aerial manipulation platform and its robotic arm, while a linear latent-space decoder supports rapid adaptation at deployment time. The framework's linear-in-parameters structure enables closed-form Bayesian updates and integration with real-time model predictive control (MPC). Experiments on a real aerial manipulation platform showed improved residual prediction accuracy, rapid adaptation after dynamics changes, and reduced MPC tracking error under changing payload conditions.
arXiv cs.RO ·