UAV avoids obstacles using only three simple sensors in real time
Learning-Based Dynamic Obstacle Avoidance for a UAV Using Only Three Range Sensors
Robotics
Summary
Navigating drones safely around obstacles, especially when those obstacles move, is hard and usually needs expensive sensors. The authors developed a way for drones to avoid both stationary and moving objects using only three cheap range sensors. They designed a smart way to represent the environment combined with a learning method so the drone can quickly decide where to go next. Tests in simulations and real flights showed this method is more successful at reaching targets without crashing than other popular techniques.
What this means in practice
- •For drone operators: Enable drones with limited sensors to safely navigate crowded environments and avoid moving obstacles in real time.
- •For autonomous vehicle engineers: Build obstacle avoidance systems for ground or aerial robots that rely on minimal directional range sensing under partial observability.
Authors
Mohammad Reza Ranjbar Divkoti, A. Pedro Aguiar
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.