19 citations · 32 across the 4 of their papers we have counts for
13 papers
Embodying Pre-Trained Word Embeddings Through Robot Actions
Minori Toyoda, Kanata Suzuki, Hiroki Mori +2
We propose a promising neural network model with which to acquire a grounded representation of robot actions and the linguistic descriptions thereof. Properly responding to various…
Spatial Attention Point Network for Deep-learning-based Robust Autonomous Robot Motion Generation
Hideyuki Ichiwara, Hiroshi Ito, Kenjiro Yamamoto +2
Deep learning provides a powerful framework for automated acquisition of complex robotic motions. However, despite a certain degree of generalization, the need for vast amounts of…
Transferable Task Execution from Pixels through Deep Planning Domain Learning
Kei Kase, Chris Paxton, Hammad Mazhar +2
While robots can learn models to solve many manipulation tasks from raw visual input, they cannot usually use these models to solve new problems. On the other hand, symbolic planni…
HATSUKI : An anime character like robot figure platform with anime-style expressions and imitation learning based action generation
Pin-Chu Yang, Mohammed Al-Sada, Chang-Chieh Chiu +6
Japanese character figurines are popular and have pivot position in Otaku culture. Although numerous robots have been developed, less have focused on otaku-culture or on embodying…
CNN-based MultiChannel End-to-End Speech Recognition for everyday home environments
Nelson Yalta, Shinji Watanabe, Takaaki Hori +2
Casual conversations involving multiple speakers and noises from surrounding devices are common in everyday environments, which degrades the performances of automatic speech recogn…
Rethinking Self-driving: Multi-task Knowledge for Better Generalization and Accident Explanation Ability
Zhihao Li, Toshiyuki Motoyoshi, Kazuma Sasaki +2
Current end-to-end deep learning driving models have two problems: (1) Poor generalization ability of unobserved driving environment when diversity of training driving dataset is l…