# Learning Mixed-Integer Convex Optimization Strategies for Robot Planning and Control

arXiv: https://arxiv.org/abs/2004.03736 · HTML: https://mlsanity.com/paper/2004.03736/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2020.

## Built on by (most cited first, 10 of 10)

- [Learning to Optimize: A Primer and A Benchmark](https://mlsanity.com/paper/2103.12828/) (2021)
- [Tutorial on amortized optimization](https://mlsanity.com/paper/2202.00665/) (2022)
- [FSNet: Feasibility-Seeking Neural Network for Constrained Optimization with Guarantees](https://mlsanity.com/paper/2506.00362/) (2025)
- [A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approaches](https://mlsanity.com/paper/2404.02817/) (2024)
- [Transformer-based Model Predictive Control: Trajectory Optimization via Sequence Modeling](https://mlsanity.com/paper/2410.23916/) (2024)
- [An actor-critic algorithm with policy gradients to solve the job shop scheduling problem using deep double recurrent agents](https://mlsanity.com/paper/2110.09076/) (2021)
- [A Differentiable Recipe for Learning Visual Non-Prehensile Planar Manipulation](https://mlsanity.com/paper/2111.05318/) (2021)
- [Is Linear Feedback on Smoothed Dynamics Sufficient for Stabilizing Contact-Rich Plans?](https://mlsanity.com/paper/2411.06542/) (2024)
- [Towards An Unsupervised Learning Scheme for Efficiently Solving Parameterized Mixed-Integer Programs](https://mlsanity.com/paper/2412.17623/) (2024)
- [Tight Constraint Prediction of Six-Degree-of-Freedom Transformer-based Powered Descent Guidance](https://mlsanity.com/paper/2501.00930/) (2025)

## Abstract (arXiv)

Mixed-integer convex programming (MICP) has seen significant algorithmic and hardware improvements with several orders of magnitude solve time speedups compared to 25 years ago. Despite these advances, MICP has been rarely applied to real-world robotic control because the solution times are still too slow for online applications. In this work, we present the CoCo (Combinatorial Offline, Convex Online) framework to solve MICPs arising in robotics at very high speed. CoCo encodes the combinatorial part of the optimal solution into a strategy. Using data collected from offline problem solutions, we train a multiclass classifier to predict the optimal strategy given problem-specific parameters such as states or obstacles. Compared to previous approaches, we use task-specific strategies and prune redundant ones to significantly reduce the number of classes the predictor has to select from, thereby greatly improving scalability. Given the predicted strategy, the control task becomes a small convex optimization problem that we can solve in milliseconds. Numerical experiments on a cart-pole system with walls, a free-flying space robot, and task-oriented grasps show that our method provides not only 1 to 2 orders of magnitude speedups compared to state-of-the-art solvers but also performance close to the globally optimal MICP solution.