CORB-Planner: Corridor as Observations for RL Planning in High-Speed Flight
On the map: Deep reinforcement learning methods → RL for robot navigation and UAV control
Abstract (arXiv)
Reinforcement learning (RL) has shown promise in a large number of robotic control tasks. Nevertheless, its deployment on unmanned aerial vehicles (UAVs) remains challenging, mainly because of reliance on accurate dynamic models and platform-specific sensing, which hinders cross-platform transfer. This paper presents the CORB-Planner (Corridor-as-Observations for RL B-spline planner), a real-time, RL-based trajectory planning framework for high-speed autonomous UAV flight across heterogeneous platforms. The key idea is to combine B-spline trajectory generation with the RL policy producing successive control points with a compact safe flight corridor (SFC) representation obtained via heuristic search. The SFC abstracts obstacle information in a low-dimensional form, mitigating overfitting to platform-specific details and reducing sensitivity to model inaccuracies. To narrow the sim-to-real gap, we adopt an easy-to-hard progressive training pipeline in simulation. A value-based soft decomposed-critic Q (SDCQ) algorithm is used to learn effective policies within approximately ten minutes of training. Benchmarks in simulation and real-world tests demonstrate real-time planning on lightweight onboard hardware and support maximum flight speeds up to 8.2m/s in dense, cluttered environments without external positioning. Compatibility with various UAV configurations (quadrotors, hexarotors) and modest onboard compute underlines the generality and robustness of CORB-Planner for practical deployment.
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 13 of its 29 references that are in the map. First posted on arXiv 14 Sep 2025.
Builds on
13 of 29 references.
References · 13
- 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
- 2015Continuous control with deep reinforcement learningcited by 3,407
- 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
- 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
- 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 604
- 2023Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learningcited by 133
- 2023STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learningcited by 89
- 2024Back to Newton's Laws: Learning Vision-based Agile Flight via Differentiable Physicscited by 45
- 2019A General Optimization-based Framework for Global Pose Estimation with Multiple Sensorscited by 44
- 2024FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometrycited by 44
- 2021DPMPC-Planner: A real-time UAV trajectory planning framework for complex static environments with dynamic obstaclescited by 15
- 2022Bubble Planner: Planning High-speed Smooth Quadrotor Trajectories using Receding Corridorscited by 10
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026High-Speed Vision-Based Flight in Clutter with Safety-Shielded Reinforcement Learning
- 2024Intercepting Unauthorized Aerial Robots in Controlled Airspace Using Reinforcement Learning
- 2024Dual Agent Learning Based Aerial Trajectory Tracking
- 2024RESC: A Reinforcement Learning Based Search-to-Control Framework for Quadrotor Local Planning in Dense Environments
- 2025LEARN: Learning End-to-End Aerial Resource-Constrained Multi-Robot Navigation
- 2026Learning-Based Dynamic Obstacle Avoidance for a UAV Using Only Three Range Sensors
- 2025Hybrid Reinforcement Learning and Search for Flight Trajectory Planning
- 2024Multi-UAV Formation Control with Static and Dynamic Obstacle Avoidance via Reinforcement Learning