Tadahrio Taniguchi

Papers

Total Citations

H-Index

About

Tadahiro Taniguchi is a pioneering researcher at the intersection of robotics, machine learning, and cognitive systems, with a primary focus on developing adaptive control mechanisms for soft-bodied robots and advancing symbol emergence in artificial intelligence. His most notable contribution is the development of learning-based control for soft robots, exemplified by his 2018 work on "Learning Oscillator-Based Gait Controller for String-Form Soft Robots Using Parameter-Exploring Policy Gradients," which has garnered 9 citations. In this study, Taniguchi introduced a novel methodology for designing mechanosensor feedback integrated with oscillator-based controllers, enabling worm-like soft robots to achieve adaptive locomotion. By employing Parameter-Exploring Policy Gradients (PEPG)—a reinforcement learning technique—he demonstrated how robots can autonomously learn to harness global entrainment between their controller, body dynamics, and environment. This work bridges biological principles with engineering, offering a pathway toward more resilient and flexible robotic systems. Taniguchi’s broader research, including his contributions to symbol emergence in robotics, positions him as a key figure in creating machines that can learn and adapt through embodied interaction, making his work highly relevant for students and researchers exploring soft robotics, embodied cognition, and bio-inspired control.