Samuel Rispal

About

Samuel Rispal is a researcher in robotic tactile sensing, focusing on how robots can interpret touch to improve object manipulation. His work centers on unsupervised feature learning for dynamic tactile events, texture roughness estimation, and texture recognition—all aimed at enabling robots to detect and respond to critical events like slippage during grasping. Rispal’s most-cited paper (2016, 32 citations) introduces a sparse coding approach to classify dynamic tactile events, a foundational method for distinguishing normal motion from problematic contact. His 2017 work on roughness estimation (4 citations) advances tactile prehension by mimicking human ability to assess surface texture from small contact areas, while his texture recognition study (2 citations) proposes object signatures to prevent mishandling. Though his citation counts are modest, Rispal’s contributions are notable for their focus on practical, real-time tactile feedback in robotic systems—a challenging area with significant implications for dexterous automation. His research bridges machine learning and sensor design, offering pathways for more adaptive and safer robotic manipulation in industrial and service applications.

Research Focus

Key Achievements

Top Papers

1. 1
   Unsupervised feature learning for classifying dynamic tactile events using sparse coding

   32 citations · 2016
2. 2
   Texture roughness estimation using dynamic tactile sensing

   4 citations · 2017
3. 3
   Textures recognition through tactile exploration for robotic applications

   2 citations · 2017

Key Collaborators

Contact & Links