# Learning-Based Dynamic Obstacle Avoidance for a UAV Using Only Three Range Sensors

arXiv: https://arxiv.org/abs/2609.14426 · HTML: https://mlsanity.com/paper/2609.14426/

## 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 14 of its 53 references that are in the map.
- First posted on arXiv 13 Sep 2026.

## Placed in

- Deep reinforcement learning methods / [RL for robot navigation and UAV control](https://mlsanity.com/deeprl/rl-for-robot-navigation-and-uav-control/)

## Builds on (most cited first, 14 of 14)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehicles](https://mlsanity.com/paper/2001.11231/) (2020)
- [A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers](https://mlsanity.com/paper/2207.00254/) (2022)
- [Motion Planning and Control for Mobile Robot Navigation Using Machine Learning: a Survey](https://mlsanity.com/paper/2011.13112/) (2020)
- [Path Planning for UAV-Mounted Mobile Edge Computing with Deep Reinforcement Learning](https://mlsanity.com/paper/2001.10268/) (2020)
- [RL-RRT: Kinodynamic Motion Planning via Learning Reachability Estimators from RL Policies](https://mlsanity.com/paper/1907.04799/) (2019)
- [Deep Reinforcement Learning for UAV Navigation Through Massive MIMO Technique](https://mlsanity.com/paper/1901.10832/) (2019)
- [Policy Optimization to Learn Adaptive Motion Primitives in Path Planning with Dynamic Obstacles](https://mlsanity.com/paper/2212.14307/) (2022)
- [ROG-Map: An Efficient Robocentric Occupancy Grid Map for Large-scene and High-resolution LiDAR-based Motion Planning](https://mlsanity.com/paper/2302.14819/) (2023)
- [Flying in Highly Dynamic Environments with End-to-end Learning Approach](https://mlsanity.com/paper/2503.14352/) (2025)
- [3D Lidar Reconstruction with Probabilistic Depth Completion for Robotic Navigation](https://mlsanity.com/paper/2207.12520/) (2022)
- [RCS: a fast path planning algorithm for Unmanned Aerial Vehicles](https://mlsanity.com/paper/1904.12283/) (2019)

## Abstract (arXiv)

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.