mlsanityData to 14 Oct 2026

FlashNav: Training Deployable Robot Navigation Policies in Seconds

arXiv 2606.15846 ↗First posted 14 Jun 2026cs.ROcited by 0

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

Abstract (arXiv)

Training Deep Reinforcement Learning (DRL) navigation policies for different robot configurations remains time-consuming. We present FlashNav, a GPU-based framework that trains robot-specific navigation policies within tens of seconds. A unified robot specification configures a lightweight simulator for batched motion updates, range sensing, and footprint collision checking over a shared occupancy map. The framework supports nonconvex footprints, different sensor configurations and drive types. Blockwise ray queries and selective observation recomputation after resets reduce simulation overhead, while GPU-resident replay and overlapping experience collection and learner updates support efficient off-policy training. Experiments covered five robot configurations and three computing platforms. With FastDSAC on a single RTX 5090 GPU, FlashNav can train a deployable navigation policy in under 30 seconds. FlashNav achieved the highest success rate and score in the benchmark comparison. The selected policies were deployed on wheeled, quadrupedal, humanoid, and irregularly shaped robots without additional policy training.

Key facts. No citing papers in the map yet (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 22 of its 33 references that are in the map. First posted on arXiv 14 Jun 2026.

Builds on

22 of 33 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024NavRL: Learning Safe Flight in Dynamic Environments24 Sep

Other references · 21

  1. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  2. 2022VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learningcited by 68
  3. 2022EnvPool: A Highly Parallel Reinforcement Learning Environment Execution Enginecited by 62
  4. 2025FastTD3: Simple, Fast, and Capable Reinforcement Learning for Humanoid Controlcited by 44
  5. 2018Reinforced Imitation: Sample Efficient Deep Reinforcement Learning for Map-less Navigation by Leveraging Prior Demonstrationscited by 38
  6. 2023DRL-VO: Learning to Navigate Through Crowded Dynamic Scenes Using Velocity Obstaclescited by 37
  7. 2023Learning to Fly in Secondscited by 31
  8. 2024No Regrets: Investigating and Improving Regret Approximations for Curriculum Discoverycited by 31
  9. 2022Rethinking Sim2Real: Lower Fidelity Simulation Leads to Higher Sim2Real Transfer in Navigationcited by 30
  10. 2020Benchmarking Metric Ground Navigationcited by 20
  11. 2021Large Batch Simulation for Deep Reinforcement Learningcited by 19
  12. 2025Learning Sim-to-Real Humanoid Locomotion in 15 Minutescited by 16
9 more
  1. 2024NeuPAN: Direct Point Robot Navigation with End-to-End Model-based Learningcited by 11
  2. 2021IPAPRec: A promising tool for learning high-performance mapless navigation skills with deep reinforcement learningcited by 10
  3. 2024HEIGHT: Heterogeneous Interaction Graph Transformer for Robot Navigation in Crowded and Constrained Environmentscited by 9
  4. 2022Deep Reinforcement Learning based Robot Navigation in Dynamic Environments using Occupancy Values of Motion Primitivescited by 6
  5. 2023Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversitycited by 3
  6. 2023Robo-centric ESDF: A Fast and Accurate Whole-body Collision Evaluation Tool for Any-shape Robotic Planningcited by 3
  7. 2026UniLab: A Heterogeneous Architecture for Robot RL Beyond GPU-Dominant Paradigmscited by 3
  8. 2026IR-SIM: A Lightweight Declarative Simulator for Navigation Learning and Benchmarkingcited by 2
  9. 2026FastDSAC: Unlocking the Potential of Maximum Entropy RL in High-Dimensional Humanoid Controlcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026120 Minutes and a Laptop: Minimalist Image-goal Navigation via Unsupervised Exploration and Offline RL
  2. 2024Deep Reinforcement Learning-based Large-scale Robot Exploration
  3. 2025VLD: Visual Language Goal Distance for Reinforcement Learning Navigation
  4. 2026FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control
  5. 2024Aquatic Navigation: A Challenging Benchmark for Deep Reinforcement Learning
  6. 2025RoboRAN: A Unified Robotics Framework for Reinforcement Learning-Based Autonomous Navigation
  7. 2026Minute-Scale Training for Microrobot Navigation ↗
  8. 2026Robostral Navigate