Yongsheng Yang

Papers

Total Citations

H-Index

About

Yongsheng Yang is a rising researcher in autonomous robotics, specializing in deep reinforcement learning (DRL) for real-world navigation and collision avoidance. His work bridges the gap between simulation and physical deployment, focusing on mapless, sensor-driven control for mobile robots and quadrotors. In his most cited paper (2023, 17 citations), Yang developed a DRL-based path planner successfully applied to a real quadrotor equipped with LIDAR, demonstrating robust autonomous flight without pre-mapped environments. His earlier work (2022, 3 citations) introduced a novel DRL algorithm for mapless collision avoidance, mapping raw sensor data directly to control commands—a critical step toward safer, more adaptive mobile robots. Though early in his career, Yang’s contributions are notable for their practical validation on physical platforms, a challenging milestone in robotics. His research holds promise for applications in search-and-rescue, warehouse automation, and autonomous delivery, where real-time decision-making in unknown spaces is essential.