Global-MPPI integrates kernel SOS global search with MPPI local refinement and graduated non-convexity smoothing to achieve faster convergence and lower costs on high-dimensional contact-rich manipulation tasks.
Real-time whole-body control of legged robots with model- predictive path integral control
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2representative citing papers
A reference-free MPPI variant with cubic Hermite spline parameterization discovers diverse emergent gaits and dynamic behaviors in legged robots by optimizing high-level objectives.
citing papers explorer
-
Global Sampling-Based Trajectory Optimization for Contact-Rich Manipulation via KernelSOS
Global-MPPI integrates kernel SOS global search with MPPI local refinement and graduated non-convexity smoothing to achieve faster convergence and lower costs on high-dimensional contact-rich manipulation tasks.
-
Reference-Free Sampling-Based Model Predictive Control
A reference-free MPPI variant with cubic Hermite spline parameterization discovers diverse emergent gaits and dynamic behaviors in legged robots by optimizing high-level objectives.