Kazuki Takahashi (M1), Department of Electrical Engineering and Information Systems, received DICOMO 2026 Outstanding Presentation Award

On 26th June 2026, Kazuki Takahashi (M1), Department of Electrical Engineering and Information Systems, received DICOMO 2026 Outstanding Presentation Award.

DICOMO 2026 Outstanding Presentation Award

The DICOMO Symposium, organized by the Information Processing Society of Japan (IPSJ), is one of the largest domestic conferences in Japan covering the fields of networking, security, and distributed systems, with a history dating back to 1997. This award is presented to particularly outstanding presentations selected from more than 200 papers delivered at the symposium.

About awarded research

In this study, we proposed a method that maps time-series signals from a 6-axis force/torque sensor embedded in a robot's fingertips into a natural language latent space using contrastive learning, thereby enabling the semantic interpretation of mechanical phenomena. This framework allows the robot to autonomously evaluate complex physical states such as the slippage, touchdown, and weight of a grasped object. Furthermore, because decision logic can be constructed through cosine similarity comparisons with language features, we demonstrated that effective robotic applications can be easily implemented without the need for traditional complex threshold tuning or mathematical definitions.

Your impression & future plan

I would like to express my sincere gratitude to the faculty members for their kind guidance throughout the writing of this paper, as well as to my laboratory members who willingly helped me practice for the conference presentation. Building upon this valuable experience, I will do my utmost to achieve even greater research outcomes in the future.