Koji Makino
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Koji Makino has a total of 78 co-authors. Here are the top co-authors by number of shared publications:
- Hidetsugu Terada
University of Yamanashi
21 shared publications - Kazuyoshi Ishida
University of Yamanashi
11 shared publications - Xiao Sun
University of Yamanashi
10 shared publications - Hiromitsu Nishizaki
University of Yamanashi
4 shared publications - Xiaoyang Mao
University of Yamanashi
4 shared publications Prawit Buayai
University of Yamanashi
3 shared publications
Latest Publications
- 14 September 2026
- Published by Springer Nature
- p. 504-514
Collision Avoidance for a Heterogeneous Multi-robot Arm System by 3D-Extended Buffered Voronoi Cells
- 14 September 2026
- Published by Springer Nature
- p. 504-514
Collision Avoidance for a Heterogeneous Multi-robot Arm System by 3D-Extended Buffered Voronoi Cells
- 20 April 2026
- Published by Fuji Technology Press Ltd. in Journal of Robotics and Mechatronics
- Vol. 38 (2) , 513-524
End-to-End Position Prediction for Robotic Grape Berry Thinning
Berry thinning is essential for producing high-quality grape varieties such as Shine Muscat because it directly impacts fruit size and quality. To address the labor-intensive nature of this task, this study presents an autonomous robotic arm system that integrates depth sensing with a learning-based transformation method and is implemented using a ResNet-18 convolutional neural network to predict berry coordinates and execute cutting actions. Its performance was compared with a geometric transformation method based on Robot Operating System 2 (ROS2) coordinate transformations in both indoor and outdoor environments. In indoor trials, the learning-based transformation approach achieved an approach accuracy of 96.8% and cutting accuracy of 78.5%, outperforming the geometric transformation approach, which achieved 94.6% for approach and 69.6% for cutting. On outdoor slopes, environmental challenges degraded the performance of both the approaches; however, the learning-based transformation method maintained higher accuracies, achieving 75.6% for approach and 60.3% for cutting, compared with the geometric transformation approach, which achieved 63.1% approach accuracy and 44.1% cutting accuracy. The complete thinning cycle required an average of 3.67 min to process 10 berries, confirming its feasibility for practical use. Limitations in the curved scissor end-effector reduced cutting effectiveness, highlighting the need for improved blade design. This study demonstrates the potential of combining geometric and learning-based transformation methods for artificial intelligence-driven robotic thinning to achieve efficient vineyard management.
- 20 April 2026
- Published by Fuji Technology Press Ltd. in Journal of Robotics and Mechatronics
- Vol. 38 (2) , 513-524
End-to-End Position Prediction for Robotic Grape Berry Thinning
Berry thinning is essential for producing high-quality grape varieties such as Shine Muscat because it directly impacts fruit size and quality. To address the labor-intensive nature of this task, this study presents an autonomous robotic arm system that integrates depth sensing with a learning-based transformation method and is implemented using a ResNet-18 convolutional neural network to predict berry coordinates and execute cutting actions. Its performance was compared with a geometric transformation method based on Robot Operating System 2 (ROS2) coordinate transformations in both indoor and outdoor environments. In indoor trials, the learning-based transformation approach achieved an approach accuracy of 96.8% and cutting accuracy of 78.5%, outperforming the geometric transformation approach, which achieved 94.6% for approach and 69.6% for cutting. On outdoor slopes, environmental challenges degraded the performance of both the approaches; however, the learning-based transformation method maintained higher accuracies, achieving 75.6% for approach and 60.3% for cutting, compared with the geometric transformation approach, which achieved 63.1% approach accuracy and 44.1% cutting accuracy. The complete thinning cycle required an average of 3.67 min to process 10 berries, confirming its feasibility for practical use. Limitations in the curved scissor end-effector reduced cutting effectiveness, highlighting the need for improved blade design. This study demonstrates the potential of combining geometric and learning-based transformation methods for artificial intelligence-driven robotic thinning to achieve efficient vineyard management.
- 5 October 2025
- Published by Springer Nature
- p. 270-279
Development of an Onion Sorting Machine with a Detachable Mechanism Using AI
- 5 October 2025
- Published by Springer Nature
- p. 270-279
Development of an Onion Sorting Machine with a Detachable Mechanism Using AI
- 5 October 2025
- Published by Springer Nature
- p. 3-13
Improved Design of an Assistive Actuator for Hip Joint with Spiral-Spring/Motor Hybrid Mechanism
- 5 October 2025
- Published by Springer Nature
- p. 3-13
Improved Design of an Assistive Actuator for Hip Joint with Spiral-Spring/Motor Hybrid Mechanism
- Open Access
- 1 May 2025
- Published by Elsevier in Smart Agricultural Technology
- Vol. 11
Feature-adaptive anomaly detection model for onion inspection system
- 1 May 2025
- Published by Elsevier in Smart Agricultural Technology
- Vol. 11
Open AccessFeature-adaptive anomaly detection model for onion inspection system
- Open Access
Development of a Rehabilitation Apparatus for Frozen Shoulder Enabling Total Motion of Shoulder Complex
This article describes an apparatus developed by the authors as a substitution for physical therapists regarding mechanical movements in the rehabilitation of frozen shoulder. In particular, the performance of this apparatus is improved in comparison with existing methods in terms of the following two major points: (1) realization of individual rehabilitation for the patient’s scapula by an innovative parallel–serial hybrid linkage design and supporting parts that can fix and move the patient’s scapula; and (2) the addition of a “teaching” and “playback” mode to enable the apparatus to record the motion of rehabilitation, allowing it to be customized for each patient by physical therapists and reproduce the recorded motion accurately, thus freeing physical therapists from repetitive rehabilitation routines. With the introduction of the whole system, experimental results are shown and discussed to verify and evaluate the performance of the developed apparatus.
Open AccessDevelopment of a Rehabilitation Apparatus for Frozen Shoulder Enabling Total Motion of Shoulder Complex
This article describes an apparatus developed by the authors as a substitution for physical therapists regarding mechanical movements in the rehabilitation of frozen shoulder. In particular, the performance of this apparatus is improved in comparison with existing methods in terms of the following two major points: (1) realization of individual rehabilitation for the patient’s scapula by an innovative parallel–serial hybrid linkage design and supporting parts that can fix and move the patient’s scapula; and (2) the addition of a “teaching” and “playback” mode to enable the apparatus to record the motion of rehabilitation, allowing it to be customized for each patient by physical therapists and reproduce the recorded motion accurately, thus freeing physical therapists from repetitive rehabilitation routines. With the introduction of the whole system, experimental results are shown and discussed to verify and evaluate the performance of the developed apparatus.
- 27 September 2024
- Published by Springer Nature
- p. 166-175
Development of a Rehabilitation Robot for the Frozen Shoulder Considering Shoulder Girdle Motion
- 27 September 2024
- Published by Springer Nature
- p. 166-175
Development of a Rehabilitation Robot for the Frozen Shoulder Considering Shoulder Girdle Motion
- 31 August 2024
- Published by Springer Nature
- p. 40-50
Improved Design of a Discontinuous Shaped Roller-Chain Drive-Type Wave Motion Reducer
- 31 August 2024
- Published by Springer Nature
- p. 40-50
Improved Design of a Discontinuous Shaped Roller-Chain Drive-Type Wave Motion Reducer
- 27 February 2024
- Published by ASME International in Journal of Mechanisms and Robotics
- Vol. 16 (9) , 1-23
Improved Design of an Orthogonal-Axis-Type Precession Motion Ball Reducer
To realize a no-backlash reducer for a small-size orthogonal-axis output, a novel design of a precession motion ball reducer is proposed. This reducer consists of a precession-motion-generating section, a motion direction converting section of the precession motion, and a reduced output-generating section. To avoid cutting tool interference, two types of distorted spatial circular grooves are located on the outer spherical surface of a precession rotor. Furthermore, the grooves of the reduced rotation generating section are profiled on the spherical surface at the output side of the precession motion rotor, which is different from the previous precession ball reducer. In this research, the equations for the groove loci of the precession motion generation, motion direction conversion, and reduced-rotation generation, which are located on the outer spherical surfaces, are proposed. The output rotating direction can be determined using the relationship between the input and output rotation angles of the precession motion direction converting groove. The prototype reducer is confirmed to smoothly rotate. Furthermore, at the hysteresis loss characteristic test, that is better than the backlash characteristic of a general orthogonal-axis output-type speed reducer with bevel gears.
- 27 February 2024
- Published by ASME International in Journal of Mechanisms and Robotics
- Vol. 16 (9) , 1-23
Improved Design of an Orthogonal-Axis-Type Precession Motion Ball Reducer
To realize a no-backlash reducer for a small-size orthogonal-axis output, a novel design of a precession motion ball reducer is proposed. This reducer consists of a precession-motion-generating section, a motion direction converting section of the precession motion, and a reduced output-generating section. To avoid cutting tool interference, two types of distorted spatial circular grooves are located on the outer spherical surface of a precession rotor. Furthermore, the grooves of the reduced rotation generating section are profiled on the spherical surface at the output side of the precession motion rotor, which is different from the previous precession ball reducer. In this research, the equations for the groove loci of the precession motion generation, motion direction conversion, and reduced-rotation generation, which are located on the outer spherical surfaces, are proposed. The output rotating direction can be determined using the relationship between the input and output rotation angles of the precession motion direction converting groove. The prototype reducer is confirmed to smoothly rotate. Furthermore, at the hysteresis loss characteristic test, that is better than the backlash characteristic of a general orthogonal-axis output-type speed reducer with bevel gears.
- Open Access
- 8 November 2023
- Published by Elsevier in Computers and Electronics in Agriculture
- Vol. 215
3D grape bunch model reconstruction from 2D images
- 8 November 2023
- Published by Elsevier in Computers and Electronics in Agriculture
- Vol. 215
Open Access3D grape bunch model reconstruction from 2D images