A new synthesis workflow converts finite-horizon minimum-time optimality into a cooling-demand VPC architecture and safety requirements into near-boundary tuning rules, matching nominal NMPC performance while showing zero temperature-limit violations under mismatch and faults where the NMPC benchmar
hub
CasADi – A software framework for nonlinear optimization and optimal con- trol
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
CAIP learns action-aligned visual representations via contrastive pre-training on human hand keypoints from egocentric video, outperforming DINOv2, SigLIP, MVP, and R3M with >30% gains on real dexterous manipulation tasks.
T-Rex introduces a large tactile dataset and MoT architecture that achieves over 30% higher success rates than baselines on 12 tasks requiring force control and deformable object handling.
DiffSlack introduces learnable slack variables and a damped Gauss-Newton projection to create a differentiable layer that enforces hard nonlinear inequality constraints in neural network outputs.
VBT-MPC performs robotic contour following by running MPC directly in vision-based tactile contour feature space and is tested on varied geometries in simulation and real experiments.
OGCVL integrates symbolic and numerical techniques to learn effective nonlinear controlled variables for scalable self-optimizing control in chemical processes.
OLAhGP optimizes receding-horizon waypoints using the Gaussian process posterior over multiple steps to produce more informative paths for environmental monitoring than prior methods.
A vectorized reformulation of global self-optimizing control makes structural causality constraints linear for batch processes and enables a shortcut method that yields simple, repetitive combination matrices for near-optimal control, shown on a fed-batch reactor.
An iterative GP-based NMPC learning scheme for batch processes achieves 83% tracking error reduction after 4 iterations and 17-fold product mass increase by iteration 8 in simulations, matching full-model NMPC performance.
A filter line search SQP algorithm reduces iterations and computation time for nonconvex SOS programs compared to prior methods.
Neural CDF barriers enable efficient planning and distributionally robust safe control for manipulators in cluttered dynamic environments using only point-cloud observations.
LSTM-based neural predictions accelerate centralized optimization for aerial-ground handover trajectories, reporting over 3x speedup and 100% success rate versus cold starts.
An open-sourced Unified Autonomy Stack fuses LiDAR, radar, vision and inertial data with sampling-based planning and control barrier functions to deliver resilient autonomy on aerial and ground robots in challenging real-world settings.
A differentiable framework integrates function encoder-based neural ODEs with predictive control to enable zero-shot adaptation of explicit policies across families of nonlinear systems.
citing papers explorer
-
A Theory-Guided Advanced Regulatory Control Synthesis for Cooling-Limited Exothermic Semi-Batch Reactors
A new synthesis workflow converts finite-horizon minimum-time optimality into a cooling-demand VPC architecture and safety requirements into near-boundary tuning rules, matching nominal NMPC performance while showing zero temperature-limit violations under mismatch and faults where the NMPC benchmar
-
Contrastive Action-Image Pre-training for Visuomotor Control
CAIP learns action-aligned visual representations via contrastive pre-training on human hand keypoints from egocentric video, outperforming DINOv2, SigLIP, MVP, and R3M with >30% gains on real dexterous manipulation tasks.
-
T-Rex: Tactile-Reactive Dexterous Manipulation
T-Rex introduces a large tactile dataset and MoT architecture that achieves over 30% higher success rates than baselines on 12 tasks requiring force control and deformable object handling.
-
DiffSlack: Learning under Nonlinear Inequality Constraints via Learnable Slack Variables
DiffSlack introduces learnable slack variables and a damped Gauss-Newton projection to create a differentiable layer that enforces hard nonlinear inequality constraints in neural network outputs.
-
VBT-MPC: Vision-Based Tactile MPC for Contour Following
VBT-MPC performs robotic contour following by running MPC directly in vision-based tactile contour feature space and is tested on varied geometries in simulation and real experiments.
-
Generalized Global Self-Optimizing Control for Chemical Processes: Part II Objective-Guided Controlled Variable Learning Approach
OGCVL integrates symbolic and numerical techniques to learn effective nonlinear controlled variables for scalable self-optimizing control in chemical processes.
-
Multi-Step Gaussian Process Propagation for Adaptive Path Planning
OLAhGP optimizes receding-horizon waypoints using the Gaussian process posterior over multiple steps to produce more informative paths for environmental monitoring than prior methods.
-
Global self-optimizing control of batch processes
A vectorized reformulation of global self-optimizing control makes structural causality constraints linear for batch processes and enables a shortcut method that yields simple, repetitive combination matrices for near-optimal control, shown on a fed-batch reactor.
-
Iterative Model-Learning Scheme via Gaussian Processes for Nonlinear Model Predictive Control of (Semi-)Batch Processes
An iterative GP-based NMPC learning scheme for batch processes achieves 83% tracking error reduction after 4 iterations and 17-fold product mass increase by iteration 8 in simulations, matching full-model NMPC performance.
-
On the Practical Implementation of a Sequential Quadratic Programming Algorithm for Nonconvex Sum-of-squares Problems
A filter line search SQP algorithm reduces iterations and computation time for nonconvex SOS programs compared to prior methods.
-
Neural Configuration-Space Barriers for Manipulation Planning and Control
Neural CDF barriers enable efficient planning and distributionally robust safe control for manipulators in cluttered dynamic environments using only point-cloud observations.
-
Learning-Accelerated Optimization-based Trajectory Planning for Cooperative Aerial-Ground Handover Missions
LSTM-based neural predictions accelerate centralized optimization for aerial-ground handover trajectories, reporting over 3x speedup and 100% success rate versus cold starts.
-
The Unified Autonomy Stack: Toward a Blueprint for Generalizable Robot Autonomy
An open-sourced Unified Autonomy Stack fuses LiDAR, radar, vision and inertial data with sampling-based planning and control barrier functions to deliver resilient autonomy on aerial and ground robots in challenging real-world settings.
-
Zero-Shot Function Encoder-Based Differentiable Predictive Control
A differentiable framework integrates function encoder-based neural ODEs with predictive control to enable zero-shot adaptation of explicit policies across families of nonlinear systems.
- Physics-informed sparse identification-based tube model predictive control for aerial vehicles