Learning for CasADi: Data-driven Models in Numerical Optimization
While real-world problems are often challenging to analyze analytically, deep learning excels in modeling complex processes from data. Existing optimization frameworks like CasADi facilitate seamless usage of solvers but face challenges when integrating learned process models into numerical optimizations. To address this gap, we present the Learning for CasADi (L4CasADi) framework, enabling the seamless integration of PyTorch-learned models with CasADi for efficient and potentially hardware-accelerated numerical optimization. The applicability of L4CasADi is demonstrated with two tutorial examples: First, we optimize a fish's trajectory in a turbulent river for energy efficiency where the turbulent flow is represented by a PyTorch model. Second, we demonstrate how an implicit Neural Radiance Field environment representation can be easily leveraged for optimal control with L4CasADi. L4CasADi, along with examples and documentation, is available under MIT license at https://github.com/Tim-Salzmann/l4casadi
Code (1)
Similar Papers 제목 키워드 기반
A Matlab and CasADi-based Implementation of RICE Dynamic Game
The most widely used integrated assessment model for studying the economics of climate change is the dynamic/regional integrated model of climate and economy (DICE/RICE). In this document, we first represent the RICE-201…
PYROBOCOP : Python-based Robotic Control & Optimization Package for Manipulation and Collision Avoidance
PYROBOCOP is a lightweight Python-based package for control and optimization of robotic systems described by nonlinear Differential Algebraic Equations (DAEs). In particular, the package can handle systems with contacts …
Collision AvoidanceLow-Latency Quasi-Static Modeling of UAV Tether Aerodynamics
One of the main limitations of multirotor UAVs is their short flight time due to battery constraints. A practical solution for continuous operation is to power the drone from the ground via a tether. While this approach …
Trajectory PlanningGreenLight-Gym: Reinforcement learning benchmark environment for control of greenhouse production systems
This study presents GreenLight-Gym, a new, fast, open-source benchmark environment for developing reinforcement learning (RL) methods in greenhouse crop production control. Built on the state-of-the-art GreenLight model,…
Numerical IntegrationReinforcement Learning (RL)Bayesian Optimization for Learning Nonlinear MPC in Autonomous Agent Navigation
Real-time autonomous navigation in dynamic, unknown environments remains a fundamental challenge for mobile robotics. We propose a map-free framework that tightly integrates reactive rolling-horizon planning with nonline…