Yasuhisa Hasegawa

Prof. Yasuhisa Hasegawa

Nagoya University
orcid

Research Focus & Metrics

Academic Career Length

33Years (1994-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2007 in Advanced Robotics
Verified
Journal Article
Closed access
KSKenta Suzuki
Kenta Suzuki
GMGouji Mito
Gouji Mito
HKHiroaki Kawamoto
Hiroaki Kawamoto
Yasuhisa HasegawaYasuhisa Hasegawa
Yasuhisa Hasegawa
YSYoshiyuki Sankai
Yoshiyuki Sankai
This paper proposes an algorithm to estimate human intentions related to walking in order to comfortably and safely support a paraplegia patient's walk. Robot Suit HAL (Hybrid Assistive Limb) has b...

1 January 2010 in Advanced Robotics
Verified
Journal Article
Open access
ATAtsushi Tsukahara
Atsushi Tsukahara
RKRyota Kawanishi
Ryota Kawanishi
Yasuhisa HasegawaYasuhisa Hasegawa
Yasuhisa Hasegawa
YSYoshiyuki Sankai
Yoshiyuki Sankai
Physical support of lower limbs during sit-to-stand and stand-to-sit transfers is important for an independent life of paraplegic patients. The purpose of this study is, therefore, to realize the c...

23 October 2014 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Closed access
ATAtsushi Tsukahara
Atsushi Tsukahara
Yasuhisa HasegawaYasuhisa Hasegawa
Yasuhisa Hasegawa
KEKiyoshi Eguchi
Kiyoshi Eguchi
YSYoshiyuki Sankai
Yoshiyuki Sankai
This paper proposes a novel gait intention estimator for an exoskeleton-wearer who needs gait support owing to walking impairment. The gait intention estimator not only detects the intention related to the start of the swing leg based on the behavior of the center of ground reaction force (CoGRF), but also infers the swing speed depending on the walking velocity. The preliminary experiments categorized into two stages were performed on a mannequin equipped with the exoskeleton robot [Hybrid Assistive Limb: (HAL)] including the proposed estimator. The first experiment verified that the gait support system allowed the mannequin to walk properly and safely. In the second experiment, we confirmed the differences in gait characteristics attributed to the presence or absence of the proposed swing speed profile. As a feasibility study, we evaluated the walking capability of a severe spinal cord injury patient supported by the system during a 10-m walk test. The results showed that the system enabled the patient to accomplish a symmetrical walk from both spatial and temporal standpoints while adjusting the speed of the swing leg. Furthermore, the critical differences of gait between our system and a knee-ankle-foot orthosis were obtained from the CoGRF distribution and the walking time. Through the tests, we demonstrated the effectiveness and practical feasibility of the gait support algorithms.

1 May 1995 in Fuzzy Sets and Systems
Verified
Journal Article
Closed access
KSKoji Shimojima
Koji Shimojima
TFToshio Fukuda
Toshio Fukuda
Yasuhisa HasegawaYasuhisa Hasegawa
Yasuhisa Hasegawa

18 June 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
HLHaokun Liu
Haokun Liu
YZYaonan Zhu
Yaonan Zhu
KKKenji Kato
Kenji Kato
ATAtsushi Tsukahara
Atsushi Tsukahara
IKIzumi Kondo
Izumi Kondo
Yasuhisa HasegawaYasuhisa Hasegawa
Yasuhisa Hasegawa
Large Language Models (LLMs) are gaining popularity in the field of robotics. However, LLM-based robots are limited to simple, repetitive motions due to the poor integration between language models, robots, and the environment. This letter proposes a novel approach to enhance the performance of LLM-based autonomous manipulation through Human-Robot Collaboration (HRC). The approach involves using a prompted GPT-4 language model to decompose high-level language commands into sequences of motions that can be executed by the robot. The system also employs a YOLO-based perception algorithm, providing visual cues to the LLM, which aids in planning feasible motions within the specific environment. Additionally, an HRC method is proposed by combining teleoperation and Dynamic Movement Primitives (DMP), allowing the LLM-based robot to learn from human guidance. Real-world experiments have been conducted using the Toyota Human Support Robot for manipulation tasks. The outcomes indicate that tasks requiring complex trajectory planning and reasoning over environments can be efficiently accomplished through the incorporation of human demonstrations.

11 September 2015 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Closed access
PDPei Di
Pei Di
Yasuhisa HasegawaYasuhisa Hasegawa
Yasuhisa Hasegawa
SNShotaro Nakagawa
Shotaro Nakagawa
KSKosuke Sekiyama
Kosuke Sekiyama
TFToshio Fukuda
Toshio Fukuda
QHQiang Huang
Qiang Huang
An intelligent walking-aid cane robot is developed for assisting the elderly and the physically challenged with walking. A motion control method is proposed for the cane robot based on human walking intention estimation. Moreover, the safety is investigated for both the cane robot and the elderly. The fall detection and prevention concepts are proposed to guarantee the safety of the elderly while walking with the cane robot. However, the deficiency of the cane robot is that it can be overturned easily because of its small size and light weight. Therefore, a controllable universal joint is designed for adjusting the tilted angle of its stick. The stability of the cane robot during the fall prevention procedure can then be enhanced by controlling the tilted angle of stick to an optimal position. A center of pressure (COP)-based fall detection (COP-FD) method is used to detect the risk of falling. In this method, the user's COP is calculated in real time using an integrated force sensory system, which comprises a six-axis force/torque sensor and an inshoe load sensor. When the COP reaches the boundary of the specified safety area, i.e., the support polygon, it is assessed that the user is going to fall down. The COP-FD method can be used in various cases of falling. However, for cases of stumbling, a rapid fall detection method is proposed based on leg motion detection, and Dubois' fuzzy possibility theory is applied to adapt to different users. When the risk of falling has been detected, a fall prevention impedance control is executed considering both the interaction compliance and system stability. In the study, a control simulation platform was established to obtain the optimal controller parameters, and all the proposed methods were finally verified through simulations and experiments.