5 papers
Projection-Retraction MPPI: Exact Constraint-Manifold Control for Manipulators
Seulchan Lee, Leesai Park, Minhyeong Kang +1
Model Predictive Path Integral (MPPI) control is widely used in manipulation for its gradient-free, parallel handling of non-convex costs. Manipulation tasks, however, often impose…
GRACE: Gradient-Free Robot Action Generation via Combined Diffusion-MPPI Posterior Mean Estimation
Leesai Park, Jiho HOng, Sanghyun Kim
Diffusion policies generate multimodal robot action sequences from demonstrations, but steering them toward deployment-time constraints typically relies on differentiable guidance…
Manifold-Constrained MPPI: Real-Time Sampling-Based Control Under Hard Constraints
Seulchan Lee, Sanghyun Kim
Sampling-based model predictive control methods, such as Model Predictive Path Integral (MPPI), offer derivative-free optimization and robustness in complex robotic systems. Howeve…
BAT: Balancing Agility and Stability via Online Policy Switching for Long-Horizon Whole-Body Humanoid Control
Donghoon Baek, Sang-Hun Kim, Sehoon Ha
Despite recent advances in control, reinforcement learning, and imitation learning, developing a unified framework that can achieve agile, precise, and robust whole-body behaviors,…
CSC-MPPI: A Novel Constrained MPPI Framework with DBSCAN for Reliable Obstacle Avoidance
Leesai Park, Keunwoo Jang, Sanghyun Kim
This paper proposes Constrained Sampling Cluster Model Predictive Path Integral (CSC-MPPI), a novel constrained formulation of MPPI designed to enhance trajectory optimization whil…