# ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation

arXiv: https://arxiv.org/abs/2008.07792 · HTML: https://mlsanity.com/paper/2008.07792/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Aug 2020.

## Built on by (most cited first, 30 of 49)

- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [Language to Rewards for Robotic Skill Synthesis](https://mlsanity.com/paper/2306.08647/) (2023)
- [BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments](https://mlsanity.com/paper/2108.03332/) (2021)
- [BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation](https://mlsanity.com/paper/2403.09227/) (2024)
- [Waypoint Models for Instruction-guided Navigation in Continuous Environments](https://mlsanity.com/paper/2110.02207/) (2021)
- [Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion](https://mlsanity.com/paper/2210.10044/) (2022)
- [Visual Room Rearrangement](https://mlsanity.com/paper/2103.16544/) (2021)
- [ManipulaTHOR: A Framework for Visual Object Manipulation](https://mlsanity.com/paper/2104.11213/) (2021)
- [Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks](https://mlsanity.com/paper/2110.03655/) (2021)
- [The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI](https://mlsanity.com/paper/2103.14025/) (2021)
- [Visual Whole-Body Control for Legged Loco-Manipulation](https://mlsanity.com/paper/2403.16967/) (2024)
- [Error-Aware Imitation Learning from Teleoperation Data for Mobile Manipulation](https://mlsanity.com/paper/2112.05251/) (2021)
- [Deep Imitation Learning for Humanoid Loco-manipulation through Human Teleoperation](https://mlsanity.com/paper/2309.01952/) (2023)
- [Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks](https://mlsanity.com/paper/2405.01534/) (2024)
- [RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation](https://mlsanity.com/paper/2402.15487/) (2024)
- [Articulated Object Interaction in Unknown Scenes with Whole-Body Mobile Manipulation](https://mlsanity.com/paper/2103.10534/) (2021)
- [Fully Autonomous Real-World Reinforcement Learning with Applications to Mobile Manipulation](https://mlsanity.com/paper/2107.13545/) (2021)
- [Self-Imitation Learning by Planning](https://mlsanity.com/paper/2103.13834/) (2021)
- [Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Robotics](https://mlsanity.com/paper/2211.02231/) (2022)
- [Robot Learning of Mobile Manipulation with Reachability Behavior Priors](https://mlsanity.com/paper/2203.04051/) (2022)
- [Generating Executable Action Plans with Environmentally-Aware Language Models](https://mlsanity.com/paper/2210.04964/) (2022)
- [Causal Policy Gradient for Whole-Body Mobile Manipulation](https://mlsanity.com/paper/2305.04866/) (2023)
- [Harmonic Mobile Manipulation](https://mlsanity.com/paper/2312.06639/) (2023)
- [Pushing it out of the Way: Interactive Visual Navigation](https://mlsanity.com/paper/2104.14040/) (2021)
- [N2M2: Learning Navigation for Arbitrary Mobile Manipulation Motions in Unseen and Dynamic Environments](https://mlsanity.com/paper/2206.08737/) (2022)
- [Distilling Motion Planner Augmented Policies into Visual Control Policies for Robot Manipulation](https://mlsanity.com/paper/2111.06383/) (2021)
- [Learning to Walk by Steering: Perceptive Quadrupedal Locomotion in Dynamic Environments](https://mlsanity.com/paper/2209.09233/) (2022)
- [Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy](https://mlsanity.com/paper/2508.13103/) (2025)
- [Practical Imitation Learning in the Real World via Task Consistency Loss](https://mlsanity.com/paper/2202.01862/) (2022)

## Abstract (arXiv)

Many Reinforcement Learning (RL) approaches use joint control signals (positions, velocities, torques) as action space for continuous control tasks. We propose to lift the action space to a higher level in the form of subgoals for a motion generator (a combination of motion planner and trajectory executor). We argue that, by lifting the action space and by leveraging sampling-based motion planners, we can efficiently use RL to solve complex, long-horizon tasks that could not be solved with existing RL methods in the original action space. We propose ReLMoGen -- a framework that combines a learned policy to predict subgoals and a motion generator to plan and execute the motion needed to reach these subgoals. To validate our method, we apply ReLMoGen to two types of tasks: 1) Interactive Navigation tasks, navigation problems where interactions with the environment are required to reach the destination, and 2) Mobile Manipulation tasks, manipulation tasks that require moving the robot base. These problems are challenging because they are usually long-horizon, hard to explore during training, and comprise alternating phases of navigation and interaction. Our method is benchmarked on a diverse set of seven robotics tasks in photo-realistic simulation environments. In all settings, ReLMoGen outperforms state-of-the-art Reinforcement Learning and Hierarchical Reinforcement Learning baselines. ReLMoGen also shows outstanding transferability between different motion generators at test time, indicating a great potential to transfer to real robots.