mlsanityData to 14 Oct 2026

Vision-driven UAV River Following: Benchmarking with Safe Reinforcement Learning

arXiv 2409.08511 ↗First posted 13 Sep 2024cs.ROcited by 2

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

Abstract (arXiv)

In this study, we conduct a comprehensive benchmark of the Safe Reinforcement Learning (Safe RL) algorithms for the task of vision-driven river following of Unmanned Aerial Vehicle (UAV) in a Unity-based photo-realistic simulation environment. We empirically validate the effectiveness of semantic-augmented image encoding method, assessing its superiority based on Relative Entropy and the quality of water pixel reconstruction. The determination of the encoding dimension, guided by reconstruction loss, contributes to a more compact state representation, facilitating the training of Safe RL policies. Across all benchmarked Safe RL algorithms, we find that First Order Constrained Optimization in Policy Space achieves the optimal balance between reward acquisition and safety compliance. Notably, our results reveal that on-policy algorithms consistently outperform both off-policy and model-based counterparts in both training and testing environments. Importantly, the benchmarking outcomes and the vision encoding methodology extend beyond UAVs, and are applicable to Autonomous Surface Vehicles (ASVs) engaged in autonomous navigation in confined waters.

Key facts. Cited by 2 papers 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 22 of its 39 references that are in the map. First posted on arXiv 13 Sep 2024.

Builds on

22 of 39 references.

References · 22

  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. 2015Continuous control with deep reinforcement learningcited by 3,407
  4. 2015Trust Region Policy Optimizationcited by 2,580
  5. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  6. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 773
  7. 2018Reward Constrained Policy Optimizationcited by 417
  8. 2018Unity: A General Platform for Intelligent Agentscited by 236
  9. 2022A Review of Safe Reinforcement Learning: Methods, Theory and Applicationscited by 181
  10. 2023Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmarkcited by 143
  11. 2020CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guaranteecited by 134
  12. 2023OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Researchcited by 80
10 more
  1. 2019Safe Policies for Reinforcement Learning via Primal-Dual Methodscited by 79
  2. 2022Penalized Proximal Policy Optimization for Safe Reinforcement Learningcited by 68
  3. 2020Learning Off-Policy with Online Planningcited by 53
  4. 2021safe-control-gym: a Unified Benchmark Suite for Safe Learning-based Control and Reinforcement Learning in Roboticscited by 50
  5. 2020Action Space Shaping in Deep Reinforcement Learningcited by 46
  6. 2019Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigationcited by 40
  7. 2022Benchmarking Reinforcement Learning Techniques for Autonomous Navigationcited by 19
  8. 2019Vision-based Navigation Using Deep Reinforcement Learningcited by 13
  9. 2022SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Drivingcited by 7
  10. 2021LVD-NMPC: A Learning-based Vision Dynamics Approach to Nonlinear Model Predictive Control for Autonomous Vehiclescited by 3

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025SafeSwarm: Decentralized Safe RL for the Swarm of Drones Landing in Dense Crowdscited by 2
  2. 2025AttentionSwarm: Reinforcement Learning with Attention Control Barier Function for Crazyflie Drones in Dynamic Environmentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Vision-driven River Following of UAV via Safe Reinforcement Learning using Semantic Dynamics Model
  2. 2024Synergistic Reinforcement and Imitation Learning for Vision-driven Autonomous Flight of UAV Along River
  3. 2025Deployable Vision-driven UAV River Navigation via Human-in-the-loop Preference Alignment
  4. 2026Lightweight Safe Reinforcement Learning for End-to-End UAV Navigation
  5. 2026RecoverFly: A Failure-Aware Reinforcement Learning Post-Training Framework for Aerial Vision-Language Navigation
  6. 2026High-Speed Vision-Based Flight in Clutter with Safety-Shielded Reinforcement Learning
  7. 2025SIGN: Safety-Aware Image-Goal Navigation for Autonomous Drones via Reinforcement Learning
  8. 2025Reinforcement Learning for Autonomous Point-to-Point UAV Navigation