Humanoid Forecast Bidirectional LSTM-based Network for Fall Prediction in a Humanoid Nov 4, 2020 learning robotics Related Humanoid Double-Support Throw Humanoid Rollover Humanoid Landing Sphere Joint Mechanism Publications Bidirectional LSTM-based Network for Fall Prediction in a Humanoid To improve on prior works, we consider a bidirectional long short-term memory (BLSTM) network, which makes use of historical measurements of system states as inputs, to effectively predict fall probability in real time. Through extensive simulation experiments, which utilize external forces with random magnitudes, directions, locations, and times of application, we demonstrate that the proposed BLSTM network can robustly predict fall events. Dongdong Liu, Hoon Jeong, Aoxue Wei, Vikram Kapila PDF Cite Project Video
