# Continuous Trajectory Planning Based on Learning Optimization in High Dimensional Input Space for Serial Manipulators

## TL;DR

This paper introduces a machine learning-based real-time trajectory planning method for high-DOF serial manipulators, utilizing input space dimension reduction to improve efficiency and enable continuous, high-dimensional trajectory generation in dynamic environments.

## Contribution

It proposes a novel learning optimization framework with input space dimension reduction, enhancing real-time trajectory planning for high-DOF manipulators in complex settings.

## Key findings

- Input space dimension reduction improves database generation efficiency.
- LO-based trajectory planning achieves real-time performance for high-dimensional inputs.
- Method validated on virtual reality haptic feedback manipulators.

## Abstract

To continuously generate trajectories for serial manipulators with high dimensional degrees of freedom (DOF) in the dynamic environment, a real-time optimal trajectory generation method based on machine learning aiming at high dimensional inputs is presented in this paper. First, a learning optimization (LO) framework is established, and implementations with different sub-methods are discussed. Additionally, multiple criteria are defined to evaluate the performance of LO models. Furthermore, aiming at high dimensional inputs, a database generation method based on input space dimension-reducing mapping is proposed. At last, this method is validated on motion planning for haptic feedback manipulators (HFM) in virtual reality systems. Results show that the input space dimension-reducing method can significantly elevate the efficiency and quality of database generation and consequently improve the performance of the LO. Moreover, using this LO method, real-time trajectory generation with high dimensional inputs can be achieved, which lays a foundation for continuous trajectory planning for high-DOF-robots in complex environments.