Laurent Perron
Papers
1
Total Citations
4
H-Index
1
About
Laurent Perron is a leading researcher in embodied artificial intelligence, with a primary focus on object-goal navigation (Object-nav) and learning-based planning under uncertainty. His most notable contribution is the development of a modular framework that leverages a contextual bandit approach to enable robots and embodied agents to navigate toward probabilistic goal configurations—moving beyond the static object targets that dominate prior work. This innovation addresses a critical gap in Embodied-AI, allowing agents to handle dynamic or uncertain object locations in real-world environments. Perron’s work has garnered attention for its practical implications in robotics and autonomous systems, with his key 2023 paper accumulating 4 citations in a rapidly evolving field. Beyond this, his research integrates reinforcement learning with hierarchical planning, offering scalable solutions for complex navigation tasks. Perron’s achievements are particularly significant for students and researchers interested in bridging the gap between simulated AI and physical-world deployment, as his methods provide a blueprint for more adaptive and robust embodied agents.
Research Focus
Key Achievements
Top Papers
- 1