M4 Control
Efficient and Accurate State Estimation and Feedback Control under Uncertainties
M4 estimates the hidden state of the running process and steers it, even though the process can be observed only partially and with noise.
Work packages
Results of the first funding phase, by work package.
-
M4.1 Stochastic filtering in large, distributed state spaces
A Newton-flow particle filter formulates the particle update as an ordinary differential equation derived from a generalised Cramér–von Mises distance. The particles keep equal weights, so the filter avoids degeneracy and global resampling. Deterministic Dirac-mixture samples reduce the number of particles needed.
Publications
-
M4.2 Accurate sensor models for state estimation
Bayesian neural networks trained with variational inference, Hamiltonian Monte Carlo and Kalman-filter backends are used as uncertainty-aware sensor models. Local calibration tests based on k-d trees, ball trees, Voronoi regions and kernels show where such models are miscalibrated, and new multivariate metrics assess calibration across all outputs.
Publications
-
FUSION, 2025
-
Trustworthy Bayesian Perceptrons
FUSION, 2024
-
Multi-Scale Uncertainty Calibration Testing for Bayesian Neural Networks Using Ball Trees
MFI, 2024
-
Voronoi Trust Regions for Local Calibration Testing in Supervised Machine Learning Models
SDF, 2024
-
Local Calibration Testing in Supervised Machine Learning Models Using Input Space Kernels
FUSION, 2025
-
Local Modified Cramér–von Mises Distance for Uncertainty Calibration Assessment in Regression
FUSION, 2026
-
Weaknesses of the ANEES and New Calibration Measures for Multivariate Predictions
MFI, 2025
-
-
M4.3 Stochastic feedback control of nonlinear distributed processes
Sampling-based model predictive control, built on the cross-entropy method and model predictive path integral control, needs no gradients and handles non-differentiable simulators such as Abaqus. Precomputed deterministic samples cover the solution space with fewer samples and give smoother control inputs. The methods were validated on benchmarks and forming simulations.
Enlarge figure Sampling-based model predictive control optimises control inputs without gradients. Trajectory shooting predicts the behaviour of the system for each sampled control trajectory and can be parallelised efficiently. Figure: KI-FOR 5339. Publications
-
ACC, 2026
-
Smooth Sampling-Based Model Predictive Control Using Deterministic Samples
23rd IFAC World Congress, 2026
-
Gaussian Homotopy Optimization with Predictor–Corrector Path Tracking and Deterministic Sampling
MFI, 2026
-
-
M4.4 Model-based policy optimisation of nonlinear distributed controllers
HEPi learns structure-aware distributed controllers in simulation with a heterogeneous graph and SE(3)-equivariant message passing, improving sample efficiency and generalisation across geometries. Learned simulators from M2, such as IGNS and STORM, could serve as fast world models for model predictive control and policy learning.
Enlarge figure Overview of the Heterogeneous Equivariant Policy (HEPi). Equivariant message passing networks process the observation graph and aggregate the actuator, object and target nodes into the action. Figure: Hoang et al., ICLR 2025. Publications
About the subproject
M4 is designed to build on the learned models of M2 and the settings found by M3. While M3 improves the process from one trial to the next, M4 is meant to keep it on track during a run. Because the forming hardware allows only feedforward actuation, the methods were validated on benchmarks and in simulation.
- Principal investigators
- Researchers
-
- Tai Hoang
- Xiaozhu Luo
- Markus Walker
- Host institute
- Intelligent Sensor-Actuator-Systems Laboratory (ISAS), KIT
Publications 13
-
Gaussian Homotopy Optimization with Predictor–Corrector Path Tracking and Deterministic Sampling
-
Local Modified Cramér–von Mises Distance for Uncertainty Calibration Assessment in Regression
-
Smooth Sampling-Based Model Predictive Control Using Deterministic Samples
-
Geometry-aware RL for Manipulation of Varying Shapes and Deformable Objects
-
Local Calibration Testing in Supervised Machine Learning Models Using Input Space Kernels
-
Weaknesses of the ANEES and New Calibration Measures for Multivariate Predictions
-
Newton-Flow Particle Filters based on Generalized Cramér Distance
-
Multi-Scale Uncertainty Calibration Testing for Bayesian Neural Networks Using Ball Trees
-
Voronoi Trust Regions for Local Calibration Testing in Supervised Machine Learning Models
-
Progressive Bayesian Particle Flows Based on Optimal Transport Map Sequences