# Deep Reactive Policy: Learning Reactive Manipulator Motion Planning for Dynamic Environments

arXiv: https://arxiv.org/abs/2509.06953 · HTML: https://mlsanity.com/paper/2509.06953/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 35 references that are in the map.
- First posted on arXiv 8 Sep 2025.

## Builds on (most cited first, 18 of 18)

- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Models](https://mlsanity.com/paper/2308.01557/) (2023)
- [Motion Planning Networks](https://mlsanity.com/paper/1806.05767/) (2018)
- [Motion Policy Networks](https://mlsanity.com/paper/2210.12209/) (2022)
- [EDMP: Ensemble-of-costs-guided Diffusion for Motion Planning](https://mlsanity.com/paper/2309.11414/) (2023)
- [STORM: An Integrated Framework for Fast Joint-Space Model-Predictive Control for Reactive Manipulation](https://mlsanity.com/paper/2104.13542/) (2021)
- [Riemannian Motion Policies](https://mlsanity.com/paper/1801.02854/) (2018)
- [Batch Informed Trees (BIT*): Sampling-based Optimal Planning via the Heuristically Guided Search of Implicit Random Geometric Graphs](https://mlsanity.com/paper/1405.5848/) (2014)
- [Broadly-Exploring, Local-Policy Trees for Long-Horizon Task Planning](https://mlsanity.com/paper/2010.06491/) (2020)
- [Adaptively Informed Trees (AIT*): Fast Asymptotically Optimal Path Planning through Adaptive Heuristics](https://mlsanity.com/paper/2002.06599/) (2020)
- [LEGO: Leveraging Experience in Roadmap Generation for Sampling-Based Planning](https://mlsanity.com/paper/1907.09574/) (2019)
- [Geometric Fabrics: Generalizing Classical Mechanics to Capture the Physics of Behavior](https://mlsanity.com/paper/2109.10443/) (2021)
- [Neural MP: A Generalist Neural Motion Planner](https://mlsanity.com/paper/2409.05864/) (2024)
- [DiffusionSeeder: Seeding Motion Optimization with Diffusion for Rapid Motion Planning](https://mlsanity.com/paper/2410.16727/) (2024)
- [Learning Implicit Sampling Distributions for Motion Planning](https://mlsanity.com/paper/1806.01968/) (2018)
- [Neural Manipulation Planning on Constraint Manifolds](https://mlsanity.com/paper/2008.03787/) (2020)
- [Learning Sampling Distributions Using Local 3D Workspace Decompositions for Motion Planning in High Dimensions](https://mlsanity.com/paper/2010.15335/) (2020)
- [Dynamically Constrained Motion Planning Networks for Non-Holonomic Robots](https://mlsanity.com/paper/2008.05112/) (2020)

## Built on by (most cited first, 9 of 9)

- [OmniGuide: Universal Guidance Fields for Enhancing Generalist Robot Policies](https://mlsanity.com/paper/2603.10052/) (2026)
- [Warm-Starting Optimization-Based Motion Planning for Robotic Manipulators via Point Cloud-Conditioned Flow Matching](https://mlsanity.com/paper/2510.03460/) (2025)
- [Toward Generalist Neural Motion Planners for Robotic Manipulators: Challenges and Opportunities](https://mlsanity.com/paper/2603.24318/) (2026)
- [Flow Motion Policy: Manipulator Motion Planning with Flow Matching Models](https://mlsanity.com/paper/2604.07084/) (2026)
- [OmniRobotHome: A Multi-Camera Home Platform for Real-Time Human-Robot Interaction](https://mlsanity.com/paper/2604.28197/) (2026)
- [ELMP: Efficient Learning for Motion Planning via Analytical Policy Gradients](https://mlsanity.com/paper/2607.00215/) (2026)
- [WeaveRL: Weaving Reconstruction into Scene-Aware Fabrics for Perceptive Reinforcement Learning](https://mlsanity.com/paper/2609.18685/) (2026)
- [Policy-Calibrated DAgger: Offline Calibrated Noise Injection for Imitation Learning](https://mlsanity.com/paper/2609.30462/) (2026)
- [Zero-Shot Reactive Obstacle Avoidance for Generative Robot Policies](https://mlsanity.com/paper/2609.35231/) (2026)

## Abstract (arXiv)

Generating collision-free motion in dynamic, partially observable environments is a fundamental challenge for robotic manipulators. Classical motion planners can compute globally optimal trajectories but require full environment knowledge and are typically too slow for dynamic scenes. Neural motion policies offer a promising alternative by operating in closed-loop directly on raw sensory inputs but often struggle to generalize in complex or dynamic settings. We propose Deep Reactive Policy (DRP), a visuo-motor neural motion policy designed for reactive motion generation in diverse dynamic environments, operating directly on point cloud sensory input. At its core is IMPACT, a transformer-based neural motion policy pretrained on 10 million generated expert trajectories across diverse simulation scenarios. We further improve IMPACT's static obstacle avoidance through iterative student-teacher finetuning. We additionally enhance the policy's dynamic obstacle avoidance at inference time using DCP-RMP, a locally reactive goal-proposal module. We evaluate DRP on challenging tasks featuring cluttered scenes, dynamic moving obstacles, and goal obstructions. DRP achieves strong generalization, outperforming prior classical and neural methods in success rate across both simulated and real-world settings. Video results and code available at https://deep-reactive-policy.com