# Reinforcement Learning with Prior Policy Guidance for Motion Planning of Dual-Arm Free-Floating Space Robot

arXiv: https://arxiv.org/abs/2209.01434 · HTML: https://mlsanity.com/paper/2209.01434/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 41 references that are in the map.
- First posted on arXiv 3 Sep 2022.

## Builds on (most cited first, 5 of 5)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Control Regularization for Reduced Variance Reinforcement Learning](https://mlsanity.com/paper/1905.05380/) (2019)
- [Motion Planner Augmented Reinforcement Learning for Robot Manipulation in Obstructed Environments](https://mlsanity.com/paper/2010.11940/) (2020)
- [Learning a Decentralized Multi-arm Motion Planner](https://mlsanity.com/paper/2011.02608/) (2020)

## Built on by (most cited first, 4 of 4)

- [DAG-Plan: Generating Directed Acyclic Dependency Graphs for Dual-Arm Cooperative Planning](https://mlsanity.com/paper/2406.09953/) (2024)
- [DRIFT: Deep Reinforcement Learning for Intelligent Floating Platforms Trajectories](https://mlsanity.com/paper/2310.04266/) (2023)
- [Trajectory Planning for Teleoperated Space Manipulators Using Deep Reinforcement Learning](https://mlsanity.com/paper/2408.05460/) (2024)
- [Phase-Gated Constrained Reinforcement Learning for End-to-End Capture and Detumbling of Non-Cooperative Targets](https://mlsanity.com/paper/2610.15491/) (2026)

## Abstract (arXiv)

Reinforcement learning methods as a promising technique have achieved superior results in the motion planning of free-floating space robots. However, due to the increase in planning dimension and the intensification of system dynamics coupling, the motion planning of dual-arm free-floating space robots remains an open challenge. In particular, the current study cannot handle the task of capturing a non-cooperative object due to the lack of the pose constraint of the end-effectors. To address the problem, we propose a novel algorithm, EfficientLPT, to facilitate RL-based methods to improve planning accuracy efficiently. Our core contributions are constructing a mixed policy with prior knowledge guidance and introducing infinite norm to build a more reasonable reward function. Furthermore, our method successfully captures a rotating object with different spinning speeds.