Papers
3
Total Citations
10
H-Index
2
About
Yasir Salam is a robotics researcher whose work lies at the intersection of autonomous navigation, multi-agent systems, and human-robot interaction. His primary research areas include deep reinforcement learning for robot navigation, hierarchical decision-making in multi-robot teams, and learning from human demonstrations. Salam’s most notable contribution is his 2025 paper on visual target-driven robot crowd navigation, which introduces a self-attention enhanced deep reinforcement learning method to help robots navigate crowded environments with limited fields of view—a significant advancement over traditional SLAM-based approaches that struggle in dynamic settings. This work has already garnered 4 citations. He also made early contributions to multi-agent robotics with his 2016 study on hierarchical multi-agent search teams, where he formulated agents using Markov decision processes to enable coordinated search in unknown areas, also accumulating 4 citations. More recently, his 2025 work “Human2bot” explores zero-shot reward function learning from human demonstrations for robotic manipulation, receiving 2 citations. Salam’s research bridges the gap between theoretical reinforcement learning and practical robotic applications, particularly in challenging real-world environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3