Real-time obstacle avoidance in mobile robots using deep reinforcement learning

Real-time obstacle avoidance is a challenge in mobile robotics, as it is an ongoing process and remains difficult to achieve in crowded, dynamic environments, where conventional planning algorithms, such as local planners, often offer limited adaptability. This paper presents a Proximal Policy Optimization-based deep reinforcement learning approach for real-time obstacle avoidance for mobile robots. The proposed system is end-to-end policy learning based on inputs from LiDAR and other auxiliary sensors, and is trained in a Gazebo-ROS environment using domain randomization to enhance robustness to sim-to-real transfer. The framework was implemented on a TurtleBot3 Burger platform and tested both in simulation and in an indoor physical environment with varying numbers of obstacles. In simulation, the proposed policy achieved a success rate of 94.2%, a 68.6% reduction in collision rate compared to the Dynamic Window Approach baseline policy, a path efficiency of 16.5%, and a 14.6% reduction in average time to goal. In real experiments, the policy has maintained success rates above 88, even under high-density conditions. The optimized onboard inference pipeline achieved less than 20 ms latency and over 50 Hz throughput on embedded hardware. These results indicate that the proposed framework is a successful and computationally feasible solution to real-time robotic navigation in dynamic environments.