Atefeh Mohajeri
Papers
1
Total Citations
6
H-Index
1
About
Atefeh Mohajeri is a robotics researcher specializing in reinforcement learning (RL) for real-world autonomous navigation and collision avoidance. Her major contributions center on bridging the gap between simulation-trained RL policies and reliable deployment on physical robots. In her most-cited work, "SACPlanner: Real-World Collision Avoidance with a Soft Actor Critic Local Planner and Polar State Representations" (2023, 6 citations), she demonstrated that enhancements to the Soft Actor Critic (SAC) algorithm—specifically RAD and DrQ—enable near-perfect training in just 10,000 episodes, producing smooth, collision-free trajectories on actual robotic platforms. This work is notable for its practical focus on polar state representations and training efficiency, addressing key challenges in sim-to-real transfer for mobile robots. Mohajeri’s research is highly relevant for students and engineers working on autonomous systems, as it provides a scalable, data-efficient framework for deploying RL-based planners in real-world environments. Her contributions underscore the importance of robust training techniques and state design in advancing field robotics.
Research Focus
Key Achievements
Top Papers
- 1