# Memory of Motion for Warm-starting Trajectory Optimization

arXiv: https://arxiv.org/abs/1907.01474 · HTML: https://mlsanity.com/paper/1907.01474/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2019.

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

- [Motion Planning Diffusion: Learning and Adapting Robot Motion Planning with Diffusion Models](https://mlsanity.com/paper/2412.19948/) (2024)
- [FlowMP: Learning Motion Fields for Robot Planning with Conditional Flow Matching](https://mlsanity.com/paper/2503.06135/) (2025)
- [PILOT: Efficient Planning by Imitation Learning and Optimisation for Safe Autonomous Driving](https://mlsanity.com/paper/2011.00509/) (2020)
- [Learning-Aided Warmstart of Model Predictive Control in Uncertain Fast-Changing Traffic](https://mlsanity.com/paper/2310.02918/) (2023)
- [Learning Multiple Initial Solutions to Optimization Problems](https://mlsanity.com/paper/2411.02158/) (2024)
- [Tensor Train for Global Optimization Problems in Robotics](https://mlsanity.com/paper/2206.05077/) (2022)
- [CoverLib: Classifiers-equipped Experience Library by Iterative Problem Distribution Coverage Maximization for Domain-tuned Motion Planning](https://mlsanity.com/paper/2405.02968/) (2024)
- [Task-Parameterized Imitation Learning with Time-Sensitive Constraints](https://mlsanity.com/paper/2312.03506/) (2023)
- [Optimal Motion Planning using Finite Fourier Series in a Learning-based Collision Field](https://mlsanity.com/paper/2312.09073/) (2023)
- [Path Database Guidance for Motion Planning](https://mlsanity.com/paper/2504.05550/) (2025)

## Abstract (arXiv)

Trajectory optimization for motion planning requires good initial guesses to obtain good performance. In our proposed approach, we build a memory of motion based on a database of robot paths to provide good initial guesses. The memory of motion relies on function approximators and dimensionality reduction techniques to learn the mapping between the tasks and the robot paths. Three function approximators are compared: k-Nearest Neighbor, Gaussian Process Regression, and Bayesian Gaussian Mixture Regression. In addition, we show that the memory can be used as a metric to choose between several possible goals, and using an ensemble method to combine different function approximators results in a significantly improved warm-starting performance. We demonstrate the proposed approach with motion planning examples on the dual-arm robot PR2 and the humanoid robot Atlas.