Sampling Strategy Design for Model Predictive Path Integral Control on Legged Robot Locomotion

• URL: http://arxiv.org/abs/2601.01409v1
• Date: Sun, 04 Jan 2026 07:25:37 GMT
• Title: Sampling Strategy Design for Model Predictive Path Integral Control on Legged Robot Locomotion
• Abstract summary: This paper systematically investigates the role of sampling strategy design within the Model Predictive Path Integral (MPPI) framework for legged robot locomotion.<n>Through extensive simulations on a quadruped robot platform, we evaluate how different sampling strategies affect control smoothness, task performance, robustness, and sample efficiency.
• Score: 6.24797585266791
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Model Predictive Path Integral (MPPI) control has emerged as a powerful sampling-based optimal control method for complex, nonlinear, and high-dimensional systems. However, directly applying MPPI to legged robotic systems presents several challenges. This paper systematically investigates the role of sampling strategy design within the MPPI framework for legged robot locomotion. Based upon the idea of structured control parameterization, we explore and compare multiple sampling strategies within the framework, including both unstructured and spline-based approaches. Through extensive simulations on a quadruped robot platform, we evaluate how different sampling strategies affect control smoothness, task performance, robustness, and sample efficiency. The results provide new insights into the practical implications of sampling design for deploying MPPI on complex legged systems.

Related papers

• Hybrid Feedback Sampling for Sample-Efficient Model Predictive Control [19.515987245507013]
  This paper shows that the optimal sampling proposal distribution can be realized by sampling with an optimized feedback policy.<n>In diverse contact-rich control tasks like humanoid loco-manipulation and dexterous manipulation, we show that FS-MPC successfully tackles dynamically unstable tasks.
  arXiv  Detail & Related papers  (2026-08-19T20:56:18Z)
• Beyond Pure Sampling: Hybrid Optimization Mechanisms for Non-Convex Model Predictive Control [16.21889938470088]
  It is shown that ME-DDP-based methods consistently outperforms DDP-based methods in low-dimensional systems where the cost is relatively simple and local information is sufficiently representative.<n>The results show that in low-dimensional systems where the cost are relatively simple and local information is sufficiently representative, our framework consistently outperforms DDP-based methods.
  arXiv  Detail & Related papers  (2026-05-30T14:09:14Z)
• TapSampling: Inference-Time Sampling with a Task-Progress-Understanding Verifier for Robotic Manipulation [61.35569005726248]
  Existing embodied control research demonstrates remarkable performance improvements by scaling training data and model size.<n>Non-deterministic generative models, such as diffusion and autoregressive models, have been widely adopted in the field of embodied control.<n>We propose textbfTapSampling, a plug-and-play framework for inference-time sampling.
  arXiv  Detail & Related papers  (2026-05-25T08:03:31Z)
• Accelerating Sampling-Based Control via Learned Linear Koopman Dynamics [4.946483489399818]
  This paper presents an efficient model predictive path integral (MPPI) control framework for systems with complex nonlinear dynamics.<n>We replace the nonlinear dynamics used for trajectory propagation with a learned linear deep Koopman operator (DKO) model, enabling faster rollout and more efficient trajectory sampling.<n>The resulting controller, termed MPPI-DK, is validated on hardware through reference-tracking experiments on a quadruped robot.
  arXiv  Detail & Related papers  (2026-03-05T17:15:52Z)
• Adaptive Linear Path Model-Based Diffusion [52.84663832658799]
  We introduce Linear Path Model-Based Diffusion (LP-MBD), which replaces the variance-preserving schedule with a flow-matching linear probability path.<n>We also propose Adaptive LP-MBD (ALP-MBD), which leverages reinforcement learning to adjust diffusion steps and noise levels according to task complexity and environmental conditions.
  arXiv  Detail & Related papers  (2026-02-02T21:33:03Z)
• Model-Based Diffusion Sampling for Predictive Control in Offline Decision Making [48.998030470623384]
  offline decision-making requires reliable behaviors from fixed datasets without further interaction.<n>We propose a compositional model-based diffusion framework consisting of: (i) a planner that generates diverse, task-aligned trajectories; (ii) a dynamics model that enforces consistency with the underlying system dynamics; and (iii) a ranker module that selects behaviors aligned with the task objectives.
  arXiv  Detail & Related papers  (2025-12-09T06:26:02Z)
• Model Tensor Planning [22.164641953175845]
  We propose emphModel Planning (MTP), a novel sampling-based MPC framework that introduces high-entropy control trajectory generation.<n>By sampling over randomized multipartite graphs, MTP ensures smooth and globally diverse control candidates.<n>Our implementation is fully vectorized using JAX and compatible with MuJoCo XLA, supporting emphJust-in-time (JIT) compilation and batched rollouts for real-time control.
  arXiv  Detail & Related papers  (2025-05-02T07:09:38Z)
• Tuning Legged Locomotion Controllers via Safe Bayesian Optimization [47.87675010450171]
  This paper presents a data-driven strategy to streamline the deployment of model-based controllers in legged robotic hardware platforms. We leverage a model-free safe learning algorithm to automate the tuning of control gains, addressing the mismatch between the simplified model used in the control formulation and the real system.
  arXiv  Detail & Related papers  (2023-06-12T13:10:14Z)
• Policy Search for Model Predictive Control with Application to Agile Drone Flight [56.24908013905407]
  We propose a policy-search-for-model-predictive-control framework for MPC. Specifically, we formulate the MPC as a parameterized controller, where the hard-to-optimize decision variables are represented as high-level policies. Experiments show that our controller achieves robust and real-time control performance in both simulation and the real world.
  arXiv  Detail & Related papers  (2021-12-07T17:39:24Z)
• Pontryagin Differentiable Programming: An End-to-End Learning and Control Framework [108.4560749465701]
  The Pontryagin Differentiable Programming methodology establishes a unified framework to solve a broad class of learning and control tasks. We investigate three learning modes of the PDP: inverse reinforcement learning, system identification, and control/planning. We demonstrate the capability of the PDP in each learning mode on different high-dimensional systems, including multi-link robot arm, 6-DoF maneuvering quadrotor, and 6-DoF rocket powered landing.
  arXiv  Detail & Related papers  (2019-12-30T15:35:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.