Nikesh Lama

Papers

Total Citations

H-Index

About

Nikesh Lama is a researcher advancing the frontier of robotic perception through tactile sensing. His work focuses on enabling robots to recognize and interact with objects using haptic data, a critical capability for autonomous manipulation in unstructured environments. In his most cited paper, "Object recognition for robotics from tactile time series data utilising different neural network architectures" (2021, 11 citations), Lama systematically investigates how Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks can extract meaningful information from tactile time series data. This research demonstrates that haptic feedback can effectively supplement or even replace visual input, allowing robots to "feel" and identify objects they grasp. By bridging deep learning with physical interaction, Lama’s contributions address a fundamental challenge in robotics: how to exploit high-quality sensory information for real-world object recognition. His work is particularly relevant for applications in manufacturing, healthcare, and assistive robotics, where visual occlusion or poor lighting limits traditional perception. Through these efforts, Lama is helping to build more capable, sensor-rich robotic systems that interact intelligently with their environment.