Riza Batista-Navarro
Papers
2
Total Citations
15
H-Index
2
About
Riza Batista-Navarro is a pioneering researcher at the intersection of robotics, natural language processing, and tactile sensing. Her work centers on two transformative areas: enabling robots to perceive and react to physical interactions through self-supervised learning, and making robot programming accessible through natural language. In her most cited work (12 citations), Batista-Navarro developed an LSTM model trained on low-cost tactile sensors that can detect object slippage during grasping—a critical capability for dexterous manipulation. By learning temporal features of micro-slippages preceding full slip events, her approach allows robots to adjust grip in real-time without expensive hardware. More recently, she has advanced human-robot collaboration through a grammar-based natural language framework for programming pick-and-place tasks (3 citations). This system uses a custom action-word dictionary to map spoken commands to robotic actions, enabling intuitive, vocabulary-expandable programming. Batista-Navarro’s contributions bridge machine learning, sensor design, and human-robot interaction, making robotic grasping more reliable and accessible. Her work has immediate applications in manufacturing, assistive robotics, and automation, where cost-effective, intelligent manipulation is essential.
Research Focus
Key Achievements
Top Papers
- 1
- 2