Rita Tse

About

Rita Tse is a researcher advancing the frontier of autonomous driving through deep reinforcement learning (RL) and 3D-LiDAR perception. Her work focuses on developing scalable, generalized RL frameworks that enable autonomous vehicles to navigate complex, real-world environments without relying on traditional supervised learning pipelines. In her highly cited 2022 paper, "Train in Austria, Race in Montecarlo: Generalized RL for Cross-Track F1tenth LIDAR-Based Races" (16 citations), she demonstrated that RL agents trained in one simulated environment can successfully transfer and race in entirely different tracks—a breakthrough for domain generalization in autonomous racing. Her complementary study, "Enabling deep reinforcement learning autonomous driving by 3D-LiDAR point clouds" (8 citations), tackles the critical challenge of processing sparse, high-dimensional LiDAR data for real-time decision-making. By integrating point cloud processing directly into RL policies, Tse’s work reduces system complexity while improving robustness. Her contributions are paving the way toward the long-held vision of fully autonomous vehicles, promising safer, more efficient transportation. With her innovative cross-track generalization and LiDAR-driven RL methods, Rita Tse is a rising voice in the quest to make robot drivers a practical reality.

Research Focus

Key Achievements

Top Papers

1. 1
   Train in Austria, Race in Montecarlo: Generalized RL for Cross-Track F1^tenth LIDAR-Based Races

   16 citations · 2022
2. 2
   Enabling deep reinforcement learning autonomous driving by 3D-LiDAR point clouds

   8 citations · 2022

Key Collaborators

Contact & Links