Etienne Roberge
Papers
4
Total Citations
53
H-Index
4
About
Etienne Roberge is a roboticist whose research sits at the intersection of tactile sensing, computer vision, and learning from demonstration, with a focus on enabling robots to perform dexterous manipulation in unstructured environments. His most influential work introduces *StereoTac*, a novel visuotactile sensor that fuses 3D vision with tactile feedback—a breakthrough that promises to dramatically improve robotic dexterity for tasks like assembly and grasping in cluttered or confined spaces (32 citations). Roberge has also made significant contributions to robot learning, developing methods to improve the generalizability of assembly tasks taught through kinesthetic demonstration, using CNN-based segmentation to correct trajectory distortions (9 citations). His research on distributed tactile sensing for safe reaching in clutter demonstrates how robots can navigate obstacles without explicit planning, relying instead on incidental contact and object motion classification (8 citations). Additionally, Roberge has advanced teaching-by-demonstration by using convolutional neural networks to detect and adapt to precise insertion tasks—a notoriously difficult challenge for collaborative robots (4 citations). Through these contributions, Roberge is shaping a future where robots can learn and adapt to complex, real-world manipulation tasks with greater autonomy and safety.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4