# Harnessing Reinforcement Learning for Neural Motion Planning

arXiv: https://arxiv.org/abs/1906.00214 · HTML: https://mlsanity.com/paper/1906.00214/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jun 2019.

## Built on by (most cited first, 21 of 21)

- [Motion Policy Networks](https://mlsanity.com/paper/2210.12209/) (2022)
- [Self-Imitation Learning by Planning](https://mlsanity.com/paper/2103.13834/) (2021)
- [Reducing Collision Checking for Sampling-Based Motion Planning Using Graph Neural Networks](https://mlsanity.com/paper/2210.08864/) (2022)
- [Motion Planning by Learning the Solution Manifold in Trajectory Optimization](https://mlsanity.com/paper/2107.05842/) (2021)
- [Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation](https://mlsanity.com/paper/2111.06383/) (2021)
- [Jacta: A Versatile Planner for Learning Dexterous and Whole-body Manipulation](https://mlsanity.com/paper/2408.01258/) (2024)
- [A Survey on the Integration of Machine Learning with Sampling-based Motion Planning](https://mlsanity.com/paper/2211.08368/) (2022)
- [Learning-based Motion Planning in Dynamic Environments Using GNNs and Temporal Encoding](https://mlsanity.com/paper/2210.08408/) (2022)
- [Efficient Motion Planning for Manipulators with Control Barrier Function-Induced Neural Controller](https://mlsanity.com/paper/2404.01184/) (2024)
- [Reinforcement Learning in Robotic Motion Planning by Combined Experience-based Planning and Self-Imitation Learning](https://mlsanity.com/paper/2306.06754/) (2023)
- [Cascaded Diffusion Models for Neural Motion Planning](https://mlsanity.com/paper/2505.15157/) (2025)
- [Bootstrapping Motor Skill Learning with Motion Planning](https://mlsanity.com/paper/2101.04736/) (2021)
- [R×R: Rapid eXploration for Reinforcement Learning via Sampling-based Reset Distributions and Imitation Pre-training](https://mlsanity.com/paper/2401.15484/) (2024)
- [Speeding up deep neural network-based planning of local car maneuvers via efficient B-spline path construction](https://mlsanity.com/paper/2203.06963/) (2022)
- [CLAMGen: Closed-Loop Arm Motion Generation via Multi-view Vision-Based RL](https://mlsanity.com/paper/2103.13267/) (2021)
- [Goal-Conditioned Supervised Learning with Sub-Goal Prediction](https://mlsanity.com/paper/2305.10171/) (2023)
- [A review of motion planning algorithms for intelligent robotics](https://mlsanity.com/paper/2102.02376/) (2021)
- [Learning from Demonstration without Demonstrations](https://mlsanity.com/paper/2106.09203/) (2021)
- [Multi-Task Option Learning and Discovery for Stochastic Path Planning](https://mlsanity.com/paper/2210.00068/) (2022)
- [Visualizing High-Dimensional Configuration Spaces: A Comprehensive Analytical Approach](https://mlsanity.com/paper/2312.10918/) (2023)
- [RoboArm-NMP: a Learning Environment for Neural Motion Planning](https://mlsanity.com/paper/2405.16335/) (2024)

## Abstract (arXiv)

Motion planning is an essential component in most of today's robotic applications. In this work, we consider the learning setting, where a set of solved motion planning problems is used to improve the efficiency of motion planning on different, yet similar problems. This setting is important in applications with rapidly changing environments such as in e-commerce, among others. We investigate a general deep learning based approach, where a neural network is trained to map an image of the domain, the current robot state, and a goal robot state to the next robot state in the plan. We focus on the learning algorithm, and compare supervised learning methods with reinforcement learning (RL) algorithms. We first establish that supervised learning approaches are inferior in their accuracy due to insufficient data on the boundary of the obstacles, an issue that RL methods mitigate by actively exploring the domain. We then propose a modification of the popular DDPG RL algorithm that is tailored to motion planning domains, by exploiting the known model in the problem and the set of solved plans in the data. We show that our algorithm, dubbed DDPG-MP, significantly improves the accuracy of the learned motion planning policy. Finally, we show that given enough training data, our method can plan significantly faster on novel domains than off-the-shelf sampling based motion planners. Results of our experiments are shown in https://youtu.be/wHQ4Y4mBRb8.