David Gonon
Papers
6
Total Citations
79
H-Index
5
About
David Gonon is a leading researcher in the field of autonomous robot navigation, with a specific focus on enabling safe and efficient movement through human crowds. His major contributions center on developing reactive control methods and evaluation frameworks for non-holonomic robots operating in densely populated environments. Gonon pioneered a novel approach for robots with convex bounding shapes to avoid imminent collisions with moving obstacles, as detailed in his highly cited 2021 work (24 citations). He also advanced the application of Inverse Reinforcement Learning to model pedestrian-robot coordination, learning cost functions from high-dimensional continuous data (14 citations). Beyond algorithmic innovation, Gonon co-created a simulation-based benchmark tool designed to systematically evaluate and compare robot crowd navigation capabilities, addressing a critical need in the robotics community (20 citations). His work on Acceleration Obstacles and self-collision avoidance further demonstrates his commitment to robust, real-world robotic systems. With a growing citation record and a clear focus on bridging the gap between laboratory research and public-space deployment, Gonon is a key figure in the quest for socially integrated autonomous robots.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Inverse Reinforcement Learning of Pedestrian–Robot Coordination14 citations · 2023
- 4
- 5Robots' Motion Planning in Human Crowds by Acceleration Obstacles5 citations · 2022
- 6