Jonathan Michaux
Papers
6
Total Citations
35
H-Index
4
About
Jonathan Michaux is an emerging robotics researcher specializing in safe motion planning, reachability analysis, and real-time control for robotic manipulators. His work addresses one of the most pressing challenges in modern robotics: enabling robot arms to operate safely and reliably alongside humans in dynamic, unstructured environments. Michaux's most significant contributions center on combining reachability-based methods with optimization and machine learning to generate provably safe motion plans in real time. His development of neural implicit safety constraints represents a notable innovation, leveraging deep learning to accelerate safety computations without sacrificing formal guarantees. He has also pioneered the use of sphere-based reachable set representations for collision avoidance, offering computationally efficient alternatives to traditional approaches. His work on uncertainty-aware planning, embodied in the ARMOUR framework, tackles the practical challenge of handling unknown object masses and inertial properties during manipulation tasks. With papers accumulating citations across venues from 2023 to 2025, Michaux has quickly established a focused and cohesive research identity. His contributions span manipulation of unsecured objects, conformal prediction for safety certification, and robust control under uncertainty — work that collectively advances the safe deployment of collaborative robots in real-world human environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6Conformalized Reachable Sets for Obstacle Avoidance with Spheres3 citations · 2025