mlsanityData to 14 Oct 2026

Enhancing Deep Reinforcement Learning-based Robot Navigation Generalization through Scenario Augmentation

arXiv 2503.01146 ↗First posted 3 Mar 2025cs.ROcited by 1

On the map: Deep reinforcement learning methods → RL for robot navigation and UAV control

Abstract (arXiv)

This work focuses on enhancing the generalization performance of deep reinforcement learning-based robot navigation in unseen environments. We present a novel data augmentation approach called scenario augmentation, which enables robots to navigate effectively across diverse settings without altering the training scenario. The method operates by mapping the robot's observation into an imagined space, generating an imagined action based on this transformed observation, and then remapping this action back to the real action executed in simulation. Through scenario augmentation, we conduct extensive comparative experiments to investigate the underlying causes of suboptimal navigation behaviors in unseen environments. Our analysis indicates that limited training scenarios represent the primary factor behind these undesired behaviors. Experimental results confirm that scenario augmentation substantially enhances the generalization capabilities of deep reinforcement learning-based navigation systems. The improved navigation framework demonstrates exceptional performance by producing near-optimal trajectories with significantly reduced navigation time in real-world applications.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods. Builds on 21 of its 39 references that are in the map. First posted on arXiv 3 Mar 2025.

Builds on

21 of 39 references.

References · 21

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  4. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,745
  5. 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 366
  6. 2018Quantifying Generalization in Reinforcement Learningcited by 352
  7. 2020Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernelcited by 187
  8. 2018Deep learning generalizes because the parameter-function map is biased towards simple functionscited by 183
  9. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 170
  10. 2017Virtual-to-real Deep Reinforcement Learning: Continuous Control of Mobile Robots for Mapless Navigationcited by 98
  11. 2021Decoupling Value and Policy for Generalization in Reinforcement Learningcited by 82
  12. 2018Reinforced Imitation: Sample Efficient Deep Reinforcement Learning for Map-less Navigation by Leveraging Prior Demonstrationscited by 38
9 more
  1. 2023DRL-VO: Learning to Navigate Through Crowded Dynamic Scenes Using Velocity Obstaclescited by 37
  2. 2021Goal-Driven Autonomous Exploration Through Deep Reinforcement Learningcited by 35
  3. 2019Assessing Transferability from Simulation to Reality for Reinforcement Learningcited by 33
  4. 2022Overcoming the Spectral Bias of Neural Value Approximationcited by 19
  5. 2022ExAug: Robot-Conditioned Navigation Policies via Geometric Experience Augmentationcited by 19
  6. 2024Semantically Controllable Augmentations for Generalizable Robot Learningcited by 18
  7. 2018Learning with Training Wheels: Speeding up Training with a Simple Controller for Deep Reinforcement Learningcited by 17
  8. 2021IPAPRec: A promising tool for learning high-performance mapless navigation skills with deep reinforcement learningcited by 10
  9. 2020Learn to Navigate Maplessly with Varied LiDAR Configurations: A Support Point-Based Approachcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Cross-Modal Reinforcement Learning for Navigation with Degraded Depth Measurementscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026NavWAM: A Navigation World Action Model for Goal-Conditioned Visual Navigation
  2. 2024Explore-Go: Leveraging Exploration for Generalisation in Deep Reinforcement Learning
  3. 2021Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing
  4. 2025HEADER: Hierarchical Robot Exploration via Attention-Based Deep Reinforcement Learning with Expert-Guided Reward
  5. 2017One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay
  6. 2024Robot Navigation with Entity-Based Collision Avoidance using Deep Reinforcement Learning
  7. 2025VLD: Visual Language Goal Distance for Reinforcement Learning Navigation
  8. 2021Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment