Program used to implement accident prediction and prevention with perception assist in Lower Limb Robot (LLR)
S. Asher and K. Kiguchi, "Real-Time Accident Prediction Using Deep Learning for," 2020 IEEE International Conference on Real-time Computing and Robotics (RCAR), 2020, pp. 333-338, doi: 10.1109/RCAR49640.2020.9303305. https://ieeexplore.ieee.org/document/9303305
Power-assist robots are useful for assisting activities of daily living (ADL) for physically weak persons. Such persons are also likely to have deteriorated perception ability, hence, it is important for power-assist robots to have perception-ability to ensure the safety of the user. Perception-assist can be accomplished by observing the interaction between the user and the environment, determining the possibility of accidents, such as falling, and preventing them by modifying the user’s motion. Therefore, in order to accomplish perception-assist, it is essential to predict the possibility of accidents in real-time.In this research, we propose a method that uses deep learning to predict the possibility of accidents based on the user’s motion, user’s motion intention from EMG signals, zero moment point (ZMP) and information from the surrounding environment. The effectiveness of the proposed method is evaluated by performing experiments to test accident-prediction and motion correction in real-time.