# Memory of Motion for Warm-starting Trajectory Optimization

## TL;DR

This paper introduces a memory-based approach for warm-starting trajectory optimization in robot motion planning, utilizing function approximators and dimensionality reduction to improve initial guesses and planning efficiency.

## Contribution

It proposes a novel memory of motion framework that leverages multiple function approximators and ensemble methods to enhance warm-starting in trajectory optimization.

## Key findings

- Ensemble of function approximators improves warm-start performance.
- Memory of motion effectively guides initial guesses for trajectory optimization.
- Method demonstrated successfully on PR2 and Atlas robots.

## Abstract

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.