Mitsuhiro Kamezaki
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Mitsuhiro Kamezaki has a total of 111 co-authors. Here are the top co-authors by number of shared publications:
- Shigeki Sugano
Waseda University, Tokyo, Japan
42 shared publications - Wen Zhao
Department of Modern Mechanical Engineering, Waseda University, Tokyo, Japan
7 shared publications - Udara Eshan Manawadu
Waseda University
6 shared publications - Yoshihiro Kawahara
The University of Tokyo
6 shared publications Hiroyasu Iwata
5 shared publications- Hiroaki Hayashi
Department of Modern Mechanical Engineering, Graduate School of Creative Science and Engineering, Waseda University, Shinjuku-ku, Tokyo, Japan
4 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (12) , 14972-14979
PhysRes-MPC: Physical Hysteretic Reservoir Computing for Embedded Control of Liquid-to-Gas Phase-Change Actuators
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (12) , 14972-14979
PhysRes-MPC: Physical Hysteretic Reservoir Computing for Embedded Control of Liquid-to-Gas Phase-Change Actuators
- 10 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (6) , 8849-8863
HeadGaze: Natural Gaze Estimation While Walking From a Single IMU on Earbuds
Gaze provides valuable insights into people’s interests and can facilitate seamless interaction with computational systems. However, capturing natural gaze during dynamic motions with compact, low-cost, low-power wearables like earbuds is challenging. While gaze estimation using IMUs has been explored, it typically requires the user to remain still or relies on additional data such as posture, limiting its use in various scenarios. In this work, we propose HeadGaze, which estimates gaze also in walking postures only from a single IMU inside an earbud with an LSTM network. We hypothesized that the acceleration caused by walking can be utilized to estimate the head orientation. To estimate gaze from head orientation, we obtained the linear head-gaze relationship coefficients. Our user study, in which participants looked freely in various postures, showed that our method estimated gaze relative to the body with an error of 12.9 degrees in the yaw direction and 10.2 degrees in the pitch direction. HeadGaze enables gaze estimation using a single IMU inside a wearable device, such as earbuds and smartglasses worn on the head, making gaze interaction techniques available on various devices. Moreover, our method essentially requires only earbuds and a smartphone for user-specific data collection without requiring special equipment such as eye trackers.
- 10 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (6) , 8849-8863
HeadGaze: Natural Gaze Estimation While Walking From a Single IMU on Earbuds
Gaze provides valuable insights into people’s interests and can facilitate seamless interaction with computational systems. However, capturing natural gaze during dynamic motions with compact, low-cost, low-power wearables like earbuds is challenging. While gaze estimation using IMUs has been explored, it typically requires the user to remain still or relies on additional data such as posture, limiting its use in various scenarios. In this work, we propose HeadGaze, which estimates gaze also in walking postures only from a single IMU inside an earbud with an LSTM network. We hypothesized that the acceleration caused by walking can be utilized to estimate the head orientation. To estimate gaze from head orientation, we obtained the linear head-gaze relationship coefficients. Our user study, in which participants looked freely in various postures, showed that our method estimated gaze relative to the body with an error of 12.9 degrees in the yaw direction and 10.2 degrees in the pitch direction. HeadGaze enables gaze estimation using a single IMU inside a wearable device, such as earbuds and smartglasses worn on the head, making gaze interaction techniques available on various devices. Moreover, our method essentially requires only earbuds and a smartphone for user-specific data collection without requiring special equipment such as eye trackers.
- Open Access
- 10 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 23971-23982
Virtual-to-Real Motion Adaptation Using Genetic Algorithm for Multi-DOF Disaster Response Robots
For disaster response robots to work safely and effectively, it is crucial to assess task executability before execution, as failures or accidents, such as rollovers, at disaster sites could cause secondary disasters. Thus, motion learning through trial and error in such environments is unacceptable. Moreover, disaster sites are highly diverse and unpredictable, making traditional pre-installed control methods ineffective due to surface slippage and unstable terrain. In this study, we propose an environment-adaptability enhancement system that enables efficient motion learning in a virtual space for multi-degree-of-freedom disaster response robots. The process begins with the robot using a depth sensor to recognize the real environment and then reconstructs it in a virtual space. The robot subsequently attempts to complete the assigned task and calculates its confidence level in successful execution. If the task fails, the robot uses a genetic algorithm to efficiently optimize control parameters using multiple virtual robots. Finally, the learned control method is applied to the real environment. Experiments verified the robot’s ability to adaptively climb higher, uneven, and slippery steps using parameters designed for standard step climbing. The results showed that the proposed system can assess task executability via confidence levels, learn viable motions in a virtual space, and successfully perform adaptive step climbing in the real-world settings.
- 10 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 23971-23982
Open AccessVirtual-to-Real Motion Adaptation Using Genetic Algorithm for Multi-DOF Disaster Response Robots
For disaster response robots to work safely and effectively, it is crucial to assess task executability before execution, as failures or accidents, such as rollovers, at disaster sites could cause secondary disasters. Thus, motion learning through trial and error in such environments is unacceptable. Moreover, disaster sites are highly diverse and unpredictable, making traditional pre-installed control methods ineffective due to surface slippage and unstable terrain. In this study, we propose an environment-adaptability enhancement system that enables efficient motion learning in a virtual space for multi-degree-of-freedom disaster response robots. The process begins with the robot using a depth sensor to recognize the real environment and then reconstructs it in a virtual space. The robot subsequently attempts to complete the assigned task and calculates its confidence level in successful execution. If the task fails, the robot uses a genetic algorithm to efficiently optimize control parameters using multiple virtual robots. Finally, the learned control method is applied to the real environment. Experiments verified the robot’s ability to adaptively climb higher, uneven, and slippery steps using parameters designed for standard step climbing. The results showed that the proposed system can assess task executability via confidence levels, learn viable motions in a virtual space, and successfully perform adaptive step climbing in the real-world settings.
- 20 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 31 (3) , 3606-3618
WAIBO: A Prototype of Water-Pipeline Inspection Robot in Murky Water, Fast Flow, and Small Obstacles
It remains a challenge for a pipeline inspection robot to traverse pipelines with water flow and obstacles and keep a smooth traversal in murky water. In this article, we developed a water-pipeline inspection robot (WAIBO) capable of resisting water flow and overcoming obstacles in murky water. WAIBO consists of two driving modules and one sensing module. The driving module has three leg wheels and a mechanism to adjust the pressure against the walls. This telescopic-pressing mechanism allows WAIBO to traverse stably by providing adequate normal force, i.e., to resist water flow and overcome obstacles. The sensing module can physically detect curved pipes using two encoders. This curve-detection mechanism allows WAIBO to control the speed of each wheel according to the turning direction and curvature, even in murky water. WAIBO is designed to resist 1 m/s of water flow and to traverse obstacles up to 10 mm in height. We performed experiments using a 15-m-long pipeline environment, including 1 m/s of water flow, six curved pipes, and three obstacles. The experimental results showed that WAIBO could smoothly overcome the obstacles using the telescopic-pressing mechanism and traverse the curved pipes using the curve-detection mechanism, without getting stuck.
- 20 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 31 (3) , 3606-3618
WAIBO: A Prototype of Water-Pipeline Inspection Robot in Murky Water, Fast Flow, and Small Obstacles
It remains a challenge for a pipeline inspection robot to traverse pipelines with water flow and obstacles and keep a smooth traversal in murky water. In this article, we developed a water-pipeline inspection robot (WAIBO) capable of resisting water flow and overcoming obstacles in murky water. WAIBO consists of two driving modules and one sensing module. The driving module has three leg wheels and a mechanism to adjust the pressure against the walls. This telescopic-pressing mechanism allows WAIBO to traverse stably by providing adequate normal force, i.e., to resist water flow and overcome obstacles. The sensing module can physically detect curved pipes using two encoders. This curve-detection mechanism allows WAIBO to control the speed of each wheel according to the turning direction and curvature, even in murky water. WAIBO is designed to resist 1 m/s of water flow and to traverse obstacles up to 10 mm in height. We performed experiments using a 15-m-long pipeline environment, including 1 m/s of water flow, six curved pipes, and three obstacles. The experimental results showed that WAIBO could smoothly overcome the obstacles using the telescopic-pressing mechanism and traverse the curved pipes using the curve-detection mechanism, without getting stuck.
- Open Access
- 21 November 2025
- Published by Wiley in Advanced Robotics Research
A Self‐Healing Permanent Magnet Putty for Soft Robot Skins With Force Sensing and Functional Recovery
Soft robotic skins require multifunctional materials that combine wireless sensing, adaptability, and autonomous self‐healing—capabilities not yet achieved by existing magnetorheological fluids, elastomers, or commercial magnetic putties. Here, permanent magnet putty (PMP) is presented, a dynamic polyborosiloxane–Ecoflex composite reinforced with high‐coercivity NdFeB microparticles. The effect of component ratios on PMP's properties is systematically investigated, and optimize the balance between fluidity and structural stability. PMP demonstrates self‐healing in both mechanical and magnetic domains. PMP restores up to 90% of its mechanical strength within 10 s after complete cutting, achieves 70% structural recovery from small deformations within 20 min, and recovers 80% of magnetic amplitude and magnetic response within 20 min. As a soft robotic skin, PMP enables precise force detection in the range of 5–30 N and exhibits up to twice the magnetic sensitivity ( B = 7.9 G) compared with commercial putties. Notably, PMP shows distinct magnetic recovery profiles that preliminarily validate its ability to discriminate pressing from cutting actions—an essential safety function in medical and industrial robotic applications. Beyond robotics, its combined wireless sensing, adaptability, and autonomous self‐healing open pathways toward wearable electronics and adaptive human–machine interfaces.
- 21 November 2025
- Published by Wiley in Advanced Robotics Research
Open AccessA Self‐Healing Permanent Magnet Putty for Soft Robot Skins With Force Sensing and Functional Recovery
Soft robotic skins require multifunctional materials that combine wireless sensing, adaptability, and autonomous self‐healing—capabilities not yet achieved by existing magnetorheological fluids, elastomers, or commercial magnetic putties. Here, permanent magnet putty (PMP) is presented, a dynamic polyborosiloxane–Ecoflex composite reinforced with high‐coercivity NdFeB microparticles. The effect of component ratios on PMP's properties is systematically investigated, and optimize the balance between fluidity and structural stability. PMP demonstrates self‐healing in both mechanical and magnetic domains. PMP restores up to 90% of its mechanical strength within 10 s after complete cutting, achieves 70% structural recovery from small deformations within 20 min, and recovers 80% of magnetic amplitude and magnetic response within 20 min. As a soft robotic skin, PMP enables precise force detection in the range of 5–30 N and exhibits up to twice the magnetic sensitivity ( B = 7.9 G) compared with commercial putties. Notably, PMP shows distinct magnetic recovery profiles that preliminarily validate its ability to discriminate pressing from cutting actions—an essential safety function in medical and industrial robotic applications. Beyond robotics, its combined wireless sensing, adaptability, and autonomous self‐healing open pathways toward wearable electronics and adaptive human–machine interfaces.
- Open Access
- 17 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 198102-198124
A Quadrotor With a New 3-DOF Hybrid Manipulator for Pipeline Maintenance: Design, Modeling, and Task-Space Control
Aerial manipulation has attracted growing interest due to the increasing demand for unmanned systems capable of performing complex tasks in hazardous or hard-to-reach environments, such as pipeline maintenance. Existing aerial manipulators often employ serial or parallel arm architectures, each with inherent limitations: serial arms offer a wide workspace but compromise stability, while parallel arms enhance stability but are restricted in orientation control and workspace range. To address these challenges, this paper presents a new aerial manipulator that integrates a quadrotor with a compact 3-DOF hybrid parallelogram-based arm and a dual-tool end-effector. The design achieves efficient task-space reachability through a cantilevered structure and improved stability via fixed-base actuation. It also enables decoupled orientation, allowing independent and precise control of the end-effector’s direction to meet task-specific requirements. Comprehensive kinematic and dynamic models are developed, and a closed-form inverse kinematics solution is derived to ensure accurate task-space positioning and motion execution. To ensure robustness under disturbances with fast convergence, smooth control signals, and reduced chattering, a hybrid control scheme is proposed that combines a backstepping controller with an adaptive disturbance estimation for position tracking, together with an adaptive fast terminal sliding mode controller featuring a singularity-free sliding surface and a continuous super-twisting reaching law for attitude and manipulator joint tracking. The controller is based on a systematic derivation approach that enables fast computation and low implementation complexity. The modeling and control framework is implemented and validated in MATLAB Simulink and Simscape, and a prototype is developed for deployment in real-world aerial manipulation scenarios.
- 17 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 198102-198124
Open AccessA Quadrotor With a New 3-DOF Hybrid Manipulator for Pipeline Maintenance: Design, Modeling, and Task-Space Control
Aerial manipulation has attracted growing interest due to the increasing demand for unmanned systems capable of performing complex tasks in hazardous or hard-to-reach environments, such as pipeline maintenance. Existing aerial manipulators often employ serial or parallel arm architectures, each with inherent limitations: serial arms offer a wide workspace but compromise stability, while parallel arms enhance stability but are restricted in orientation control and workspace range. To address these challenges, this paper presents a new aerial manipulator that integrates a quadrotor with a compact 3-DOF hybrid parallelogram-based arm and a dual-tool end-effector. The design achieves efficient task-space reachability through a cantilevered structure and improved stability via fixed-base actuation. It also enables decoupled orientation, allowing independent and precise control of the end-effector’s direction to meet task-specific requirements. Comprehensive kinematic and dynamic models are developed, and a closed-form inverse kinematics solution is derived to ensure accurate task-space positioning and motion execution. To ensure robustness under disturbances with fast convergence, smooth control signals, and reduced chattering, a hybrid control scheme is proposed that combines a backstepping controller with an adaptive disturbance estimation for position tracking, together with an adaptive fast terminal sliding mode controller featuring a singularity-free sliding surface and a continuous super-twisting reaching law for attitude and manipulator joint tracking. The controller is based on a systematic derivation approach that enables fast computation and low implementation complexity. The modeling and control framework is implemented and validated in MATLAB Simulink and Simscape, and a prototype is developed for deployment in real-world aerial manipulation scenarios.
- Open Access
- 17 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (12) , 12676-12683
SPIRA: Small Gas Pipeline Inspection Robot With Spiral Leg-Wheel Mechanism and Single Bending Joint
Gas pipelines damaged by aging or earthquakes need a robotic system that can quickly inspect 50-mm-diameter service lines, consisting of horizontal and vertical pipes connected by elbow joints, tees, or sockets, from the inside. However, conventional pipe inspection robots do not target 50-mm pipes and various pipe types or lack sufficient speed and a reverse function. Thus, this study develops an in-pipe inspection robot, SPIRA, capable of traveling through 50-mm pipelines while meeting the above requirements. SPIRA has three wheels inclined at 30 degrees to the horizontal, arranged around a cylinder. The cylinder is rotated by a motor around the robot’s axis, and the wheels move in a spiral motion while pushing the pipe wall, enabling the robot to move stably and quickly. To overcome socket steps of up to 3 mm and diameter changes in elbow joints, the cylinder and each wheel are connected by a leg with a spring pantograph mechanism. SPIRA has two traveling units linked by a bending joint with a servomotor. When the front and rear parts rotate clockwise (counterclockwise), SPIRA moves forward (backward). When both units rotate in the opposite direction, only the central part of SPIRA rotates on the spot, changing the bending direction so that SPIRA can select any travel direction in a tee. We evaluated the travel performance of SPIRA in a pipeline of horizontal, vertical, elbow joints, tees, or sockets, and found that it could smoothly travel through the pipelines, which is difficult for conventional robot systems to achieve.
- 17 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (12) , 12676-12683
Open AccessSPIRA: Small Gas Pipeline Inspection Robot With Spiral Leg-Wheel Mechanism and Single Bending Joint
Gas pipelines damaged by aging or earthquakes need a robotic system that can quickly inspect 50-mm-diameter service lines, consisting of horizontal and vertical pipes connected by elbow joints, tees, or sockets, from the inside. However, conventional pipe inspection robots do not target 50-mm pipes and various pipe types or lack sufficient speed and a reverse function. Thus, this study develops an in-pipe inspection robot, SPIRA, capable of traveling through 50-mm pipelines while meeting the above requirements. SPIRA has three wheels inclined at 30 degrees to the horizontal, arranged around a cylinder. The cylinder is rotated by a motor around the robot’s axis, and the wheels move in a spiral motion while pushing the pipe wall, enabling the robot to move stably and quickly. To overcome socket steps of up to 3 mm and diameter changes in elbow joints, the cylinder and each wheel are connected by a leg with a spring pantograph mechanism. SPIRA has two traveling units linked by a bending joint with a servomotor. When the front and rear parts rotate clockwise (counterclockwise), SPIRA moves forward (backward). When both units rotate in the opposite direction, only the central part of SPIRA rotates on the spot, changing the bending direction so that SPIRA can select any travel direction in a tee. We evaluated the travel performance of SPIRA in a pipeline of horizontal, vertical, elbow joints, tees, or sockets, and found that it could smoothly travel through the pipelines, which is difficult for conventional robot systems to achieve.
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Appearance-Independent Tactile Design Using Different Embroidery Stitches
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Open AccessAppearance-Independent Tactile Design Using Different Embroidery Stitches
- 27 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (5) , 4994-5001
Joint-Repositionable Inner-Wireless Planar Snake Robot
Bio-inspired multi-joint snake robots offer the advantages of terrain adaptability due to their limbless structure and high flexibility. However, a series of dozens of motor units in typical multiple-joint snake robots results in a heavy body structure and hundreds of watts of high power consumption. This paper presents a joint-repositionable, inner-wireless snake robot that enables multi-joint-like locomotion using a low-powered underactuated mechanism. The snake robot, consisting of a series of flexible passive links, can dynamically change its joint coupling configuration by repositioning motor-driven joint units along rack gears inside the robot. Additionally, a soft robot skin wirelessly powers the internal joint units, avoiding the risk of wire tangling and disconnection caused by the movable joint units. The combination of the joint-repositionable mechanism and the wireless-charging-enabled soft skin achieves a high degree of bending, along with a lightweight structure of 1.3 kg and energy-efficient wireless power transmission of 7.6 watts.
- 27 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (5) , 4994-5001
Joint-Repositionable Inner-Wireless Planar Snake Robot
Bio-inspired multi-joint snake robots offer the advantages of terrain adaptability due to their limbless structure and high flexibility. However, a series of dozens of motor units in typical multiple-joint snake robots results in a heavy body structure and hundreds of watts of high power consumption. This paper presents a joint-repositionable, inner-wireless snake robot that enables multi-joint-like locomotion using a low-powered underactuated mechanism. The snake robot, consisting of a series of flexible passive links, can dynamically change its joint coupling configuration by repositioning motor-driven joint units along rack gears inside the robot. Additionally, a soft robot skin wirelessly powers the internal joint units, avoiding the risk of wire tangling and disconnection caused by the movable joint units. The combination of the joint-repositionable mechanism and the wireless-charging-enabled soft skin achieves a high degree of bending, along with a lightweight structure of 1.3 kg and energy-efficient wireless power transmission of 7.6 watts.
- 10 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (4) , 3286-3293
Predictive Energy Stability Margin: Prediction of Heavy Machine Overturning Considering Rotation and Translation
Fatal accidents caused by the overturning of heavy machines still happen, so the prediction and prevention of overturns are urgently needed. Indicators to evaluate overturn, such as the energy stability margin (ESM), have been proposed but are limited to a non-slip ground surface. Even if ESM is above zero, the machine may overturn due to additional manipulator operation or hitting an obstacle while sliding down a slope. This study thus proposes a predictive energy stability margin, pp-ESM, that focuses on kinetic energy in the translational and rotational directions for overturn prediction. Rotational kinetic energy EERR accelerates overturning, and the translational kinetic energy EETT in the slope direction is converted to EERR. Both are calculated from the mass and the position and acceleration of the center of gravity (COG) for each part of the machine. ESM UU is defined as the difference between the height of COG just before overturn and the current height of the COG. Thus, pp-ESM is defined as UU minus the sum of EERR and EETT. We also developed an operation support system to limit the manipulator operation by using pp-ESM. The results of experiments using a hydraulically driven scale model (1/14) with different combinations of operations, loading weights, and ground surfaces confirmed that pp-ESM can predict overturns early and accurately, which conventional ESM cannot do. We also found that the support system using pp-ESM can prevent inappropriate operations and avoid overturns.
- 10 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (4) , 3286-3293
Predictive Energy Stability Margin: Prediction of Heavy Machine Overturning Considering Rotation and Translation
Fatal accidents caused by the overturning of heavy machines still happen, so the prediction and prevention of overturns are urgently needed. Indicators to evaluate overturn, such as the energy stability margin (ESM), have been proposed but are limited to a non-slip ground surface. Even if ESM is above zero, the machine may overturn due to additional manipulator operation or hitting an obstacle while sliding down a slope. This study thus proposes a predictive energy stability margin, pp-ESM, that focuses on kinetic energy in the translational and rotational directions for overturn prediction. Rotational kinetic energy EERR accelerates overturning, and the translational kinetic energy EETT in the slope direction is converted to EERR. Both are calculated from the mass and the position and acceleration of the center of gravity (COG) for each part of the machine. ESM UU is defined as the difference between the height of COG just before overturn and the current height of the COG. Thus, pp-ESM is defined as UU minus the sum of EERR and EETT. We also developed an operation support system to limit the manipulator operation by using pp-ESM. The results of experiments using a hydraulically driven scale model (1/14) with different combinations of operations, loading weights, and ground surfaces confirmed that pp-ESM can predict overturns early and accurately, which conventional ESM cannot do. We also found that the support system using pp-ESM can prevent inappropriate operations and avoid overturns.