MPPI Control

MPPI: Model Predictive Path Integral

MPPI control repeatedly simulates candidate action sequences, weights them by their predicted costs, and applies the best-informed action before replanning from the latest state. It is useful for nonlinear, contact-rich, or otherwise difficult-to-optimize systems, including robots, drones, and vehicles. Common approaches improve sampling with feedback policies, motion primitives, or learned priors; accelerate rollouts with GPU simulation or learned dynamics; and incorporate safety through constraints, barrier functions, or uncertainty-aware costs. A central challenge is balancing computation and model accuracy with reliable safety: sparse samples and model mismatch can misrank trajectories, while averaging distinct good behaviors can produce a poor action.

Latest papers

40 papers4 papers in the last four weeks, down 50% on the four weeks before. 0.0% of all new papers.

RAY-TOLD: Ray-Based Latent Dynamics for Dense Dynamic Obstacle Avoidance with TDMPC
Apr 30, 2026Seungho Han, Seokju Lee, Jeonguk KangRobot Navigation MPPI Control
School of Electrical Engineering, Hanyang University, Ansan 15588, South Korea. · Mechatronics, Systems and Control Lab (MSC Lab), Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon 34141, South Korea. · Samsung Research, Samsung Electronics, Seoul, South Korea.
Lexicographic Minimum-Violation Motion Planning using Signal Temporal Logic
Apr 22, 2026Patrick Halder, Lothar Kiltz, Hannes Homburger +2STL Motion Planning Motion Planning
School of Computation, Information and Technology, Technical University of Munich, 85748 Garching, Germany · 2ZF Friedrichshafen AG, 88046 Friedrichshafen, Germany · Institute of System Dynamics, HTWG Konstanz, 78562 Konstanz, Germany
COSMIK-MPPI: Scaling Constrained Model Predictive Control to Collision Avoidance in Close-Proximity Dynamic Human Environments
Apr 11, 2026Ege Gursoy, Maxime Sabbah, Arthur Haffemayer +5Robot Collision Avoidance Model Predictive Control
LAAS-CNRS, Université de Toulouse, CNRS, Toulouse, France · CIIRC, Czech Technical University, Prague · LIRMM, Université de Montpellier, CNRS, Montpellier, France +3
Risk-Constrained Belief-Space Optimization for Safe Control under Latent Uncertainty
Apr 4, 2026Clinton Enwerem, John S. Baras, Calin BeltaBelief-Space Planning Safety-Critical Control
Institute for Systems Research, University of Maryland, College Park, MD, USA
Model Predictive Path Integral PID Control for Learning-Based Path Following
Mar 31, 2026Teruki Kato, Koshi Oishi, Seigo ItoNonlinear MPC Residual Dynamics Learning
Toyota Central R&D Labs., Inc., Nagakute 480-1192, Japan
Vision-Guided MPPI for Agile Drone Racing: Navigating Arbitrary Gate Poses via Neural Signed Distance Fields
Mar 7, 2026Fangguo Zhao, Hanbing Zhang, Zhouheng Li +2Autonomous Drone Racing Aerial Robotics
College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China
Accelerating Sampling-Based Control via Learned Linear Koopman Dynamics
Mar 5, 2026Wenjian Hao, Yuxuan Fang, Zehui Lu +1Robotic Control Robot Trajectory Tracking
independent researcher
Reactive Motion Generation With Particle-Based Perception in Dynamic Environments
Feb 18, 2026Xiyuan Zhao, Huijun Li, Lifeng Zhu +3Robot Motion Generation Dynamic Obstacle Avoidance
The authors are with the State Key Laboratory of Digital Medical Engineering, Jiangsu Key Lab of Robot Sensing and Control, School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China.
Stein-based Optimization of Sampling Distributions in Model Predictive Path Integral Control
Nov 3, 2025Jace Aldrich, Odest Chadwicke JenkinsRobotic Control Stochastic Optimal Control
Laboratory for Perceptive RObotics and Grounded REasoning SystemS and Robotics Department at the University of Michigan, Ann Arbor, USA
BR-MPPI: Barrier-Rate Guided MPPI for Enforcing Multiple Inequality Constraints with Learned Signed Distance Fields
Jun 8, 2025Hardik Parwana, Taekyung Kim, Kehan Long +4Constrained Motion Planning Control Barrier Functions
Robotics Department, University of Michigan, Ann Arbor, MI 48109, USA · Contextual Robotics Institute, University of California San Diego, La Jolla, CA 92093, USA. · Toyota Motor North America, Research & Development, Ann Arbor, MI 48105, USA.

Apr 30, 2026J/K move · Enter open · S save

RAY-TOLD: Ray-Based Latent Dynamics for Dense Dynamic Obstacle Avoidance with TDMPC

Seungho Han, Seokju Lee, Jeonguk Kang

School of Electrical Engineering, Hanyang University, Ansan 15588, South Korea. · Mechatronics, Systems and Control Lab (MSC Lab), Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon 34141, South Korea. · Samsung Research, Samsung Electronics, Seoul, South Korea.

Robot Navigation MPPI Control Dynamic Obstacle Avoidance Robot Motion Planning Model-Based RL

Open paper AskPDF arXiv

Dense, dynamic crowds pose a persistent challenge for autonomous mobile robots. Purely reactive planning methods, such as Model Predictive Path Integral (MPPI) control, often fail to escape local minima in complex scenarios due to their limited prediction horizon. To bridge this gap, we propose Ray-based Task-Oriented Latent Dynamics (RAY-TOLD), a hybrid control architecture that integrates obstacle information into latent dynamics and utilizes the robustness of physics-based MPPI with the long-horizon foresight of reinforcement learning. RAY-TOLD leverages a LiDAR-centric latent dynamics model to encode high-dimensional sensor data into a compact state representation, enabling the learning of a terminal value function and a policy prior. We introduce a policy mixture sampling strategy that augments the MPPI candidate population with trajectories derived from the learned policy, effectively guiding the planner towards the goal while maintaining kinematic feasibility. Extensive tests in a stochastic environment with high-density dynamic obstacles demonstrate that our method outperforms the MPPI baseline, reducing the collision rate. The results confirm that blending short-horizon physics-based rollouts with learned long-horizon intent significantly enhances navigation reliability and safety.