Papers
24
Total Citations
299
H-Index
9
About
Israel Becerra is a robotics researcher whose work spans motion planning, pursuit-evasion games, visual control, and human-robot interaction, with growing contributions to deep learning and reinforcement learning in robotics. His most widely recognized work, a comprehensive survey on deep learning and deep reinforcement learning in robotics (2021, 93 citations), has become an essential reference for researchers entering these rapidly evolving fields. Becerra has made significant theoretical contributions to visibility-based pursuit-evasion problems, examining how nonholonomic robots can track or evade opponents in complex environments, and exploring the strategic value of information in differential games. His work on VR-based telepresence introduced a novel motion planning framework that balances presence and comfort for remotely immersed users, addressing the critical challenge of cybersickness. He has also advanced sampling-based planning through analysis of local planners within the RRT* framework, and explored unconventional robot locomotion strategies such as bouncing motion patterns. Additional contributions include image-based visual servoing integrated into planning pipelines and mobile robot object confirmation methods. Through a body of work combining rigorous theory with practical robotics applications, Becerra has established himself as a versatile and impactful figure in autonomous systems research.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Human perception-optimized planning for comfortable VR-based telepresence22 citations · 2020
- 4
- 5
- 6
- 7
- 8
- 9Visual-RRT: Integrating IBVS as a steering method in an RRT planner9 citations · 2023
- 10On the value of information in a differential pursuit-evasion game8 citations · 2015