SHIMA Lab's Activities
Research Contents
Supporting humans with human mechanism x intelligent robot
Humans usually reach out and grab distant objects, and casually perform various movements such as walking and running without falling. However, in order to perform these movements naturally, it is necessary to contract a large number of muscles in a well-balanced manner and perform them with appropriate force and timing. In addition, humans can acquire various information by actions such as seeing something with their eyes or feeling it with their skin, and can make various judgments and predictions based on the current situation and past experience．
In this way, human beings are extremely complex and advanced information processing systems, and are made up of a wide variety of mechanisms. These mechanisms are still not fully understood, and they may have hidden hints for efficient human support. For example, it is possible to effectively support humans by appropriately measuring and evaluating biological signals (electromyograms, mechanomyograms, brain waves, vitals, etc.) generated by human activities．
In our laboratory, we elucidate the principle of the mechanism that realizes the skillful movement of humans and apply intelligent robot technology equipped with artificial intelligence that thinks and judges flexibly like humans, and effectively humans in various scenes. We are conducting research activities with the aim of supporting humans．
The research themes are centered on the following four．
Artificial intelligence model that realizes high-speed and high-precision separation
Construction of original learning theory based on probabilistic model and development of artificial intelligence chip that is human-like and surpasses human
- Aiming at application to medical, welfare, industrial fields, etc., we are researching pattern recognition models such as new neural network knowledge and support vector machines that introduce probabilistic models, and aim to develop human-like artificial intelligence that surpasses humans. In addition, we are implementing hardware using FPGA with the aim of integrating neural networks and various systems into a single chip．
＜Example of applied theme＞
- Neural network model that realizes probabilistic pattern recognition
- Unlearned class estimation model with complementary event distribution
- Pulse neuron model considering hardware implementation
- Evolved neuron chip using FPGA
Human-machine interface using biological signals
Devising a human support interface system using an artificial intelligence model
- Devising a human support interface system using an artificial intelligence model by estimating human movements and intentions from biological signals, we are taking on the challenge of developing a new interface that can control artificial hands, various devices around us, robots, and so on．
＜Example of applied theme＞
- New game interface
- Control of mobile robots
- 5-finger-driven myoelectric prosthetic hand
- Brain machine interface
- Virtual reaction force presentation device
Biological signal analysis and human model aimed at elucidating the motor mechanism
Proposal of a mathematical model that expresses the mechanisms of the skillful human nervous system, motor system, and sensory system
- We are working on body movement measurement and analysis using accelerometers and magnetic sensors, including bioelectrical signals such as electromyogram (EMG), mechanomyogram (MMG), and electroencephalogram (EEG)．
- In order to clarify what kind of physical information the biological signals reflect and how humans are exercising, we are constructing a human model that expresses sensations, neural functions, and musculoskeletal functions．
＜Example of applied theme＞
- Elucidation of the mechanism of light touch contact and standing model
- Infant behavior and functional development model
- Somatosensory stimulus perceptual characteristic model
- CNeural activity model based on the Central Pattern Generator group
Motor function evaluation,training method that efficiently supports doctors,therapists and patients
Medical support based on human model and artificial intelligence model
- Quantification of illness , motor function and diagnosis , training support system By applying biometric signal analysis technology to medical technology, development of a system that supports doctor's diagnosis and rehabilitation of therapists and new findings on illness, dysfunction I am aiming for discovery．
＜Example of applied theme＞
- Devising a fall prevention method using a virtual wall and evaluating its function
- Motion transmission and motor learning support using multi-channel electrical stimulation
- Evaluation of developmental function by infant behavior analysis
- Parkinson's disease evaluation based on finger tap motion analysis