aiqbench analysis
This research demonstrates a Deep Reinforcement Learning approach enabling UAVs to navigate dynamic environments using only three low-cost range sensors, eliminating the need for expensive LiDAR or vision systems. By co-designing a behavior grid map with Proximal Policy Optimization, the method achieves superior success rates in high-congestion scenarios compared to standard PPO and Model Predictive Control variants. The study validates practical feasibility through real-world experiments, offering a scalable solution for autonomous navigation under extreme partial observability.
Learning-Based Dynamic Obstacle Avoidance for a UAV Using Only Three Range Sensors
arXiv:2609.14426v1 Announce Type: new Abstract: We present a learning-based approach to kinodynamic online motion planning for an Unmanned Aerial Vehicle (UAV) operating at a fixed altitude in unknown dynamic environments, where real-time avoidance of both static and dynamic obstacles must be achieved under conditions of extreme partial observability. The UAV is controlled with a single degree of freedom (yaw only), resulting in constrained, nonholonomic motion similar to fixed-wing platforms. The proposed framework integrates a behavior grid map representation with Deep Reinforcement Learning (DRL), using Proximal Policy Optimization (PPO) for stable policy learning in continuous control. The key idea is the co-design of a state representation and control policy that enables reliable navigation using only three low-cost directional range sensors, without reliance on dense sensing modalities such as LiDAR or vision-based systems. The behavior grid map dynamically aggregates sparse measurements into a structured local representation that supports real-time decision-making for obstacle avoidance and target reaching. Extensive simulations across environments of varying sizes and obstacle densities demonstrate that the proposed standard and enhanced methods achieve higher success rates than PPO variants and Model Predictive Control (MPC) (94\% vs. 79--90\% in small-scale high-congestion scenarios, and 83\% vs. 62--71\% in large-scale high-congestion scenarios), while maintaining real-time performance. Real-world experiments across four scenarios further confirm practical feasibility, with consistent target-reaching behaviour and no collisions under the tested conditions.
Abstract:We present a learning-based approach to kinodynamic online motion planning for an Unmanned Aerial Vehicle (UAV) operating at a fixed altitude in unknown dynamic environments, where real-time avoidance of both static and dynamic obstacles must be achieved under conditions of extreme partial observability. The UAV is controlled with a single degree of freedom (yaw only), resulting in constrained, nonholonomic motion similar to fixed-wing platforms. The proposed framework integrates a behavior grid map representation with Deep Reinforcement Learning (DRL), using Proximal Policy Optimization (PPO) for stable policy learning in continuous control. The key idea is the co-design of a state representation and control policy that enables reliable navigation using only three low-cost directional range sensors, without reliance on dense sensing modalities such as LiDAR or vision-based systems. The behavior grid map dynamically aggregates sparse measurements into a structured local representation that supports real-time decision-making for obstacle avoidance and target reaching. Extensive simulations across environments of varying sizes and obstacle densities demonstrate that the proposed standard and enhanced methods achieve higher success rates than PPO variants and Model Predictive Control (MPC) (94\% vs. 79--90\% in small-scale high-congestion scenarios, and 83\% vs. 62--71\% in large-scale high-congestion scenarios), while maintaining real-time performance. Real-world experiments across four scenarios further confirm practical feasibility, with consistent target-reaching behaviour and no collisions under the tested conditions.
Robotics (cs.RO); Systems and Control (eess.SY)
arXiv:2609.14426 [cs.RO]
(or arXiv:2609.14426v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.14426 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 315 words
Related coverage
Lattice-Based Cryptography Explained
Quantum Zeitgeist · Aug 15, 2026
DODGER: Safety-Guided Reinforcement Learning for Robot Navigation Among Dynamic Obstacles
arXiv · Oct 1, 2026
Reactive 3D Motion Planning for a Franka Arm via Star-World Workspace Reshaping
arXiv · Jul 29, 2026
Safe Multi-Robot Collaborative Transport Using Density Functions
arXiv · Oct 7, 2026