A Framework of Explanation Generation toward Reliable Autonomous Robots

no code implementations • 6 May 2021 • Tatsuya Sakai, Kazuki Miyazawa, Takato Horii, Takayuki Nagai

It was inferred from the result of a simulation experiment that the explanation generated using the proposed method was composed of the minimum elements important for understanding the transition from the current state to the target state.

Decision Making Explanation Generation

lamBERT: Language and Action Learning Using Multimodal BERT

no code implementations • 15 Apr 2020 • Kazuki Miyazawa, Tatsuya Aoki, Takato Horii, Takayuki Nagai

Recently, the bidirectional encoder representations from transformers (BERT) model has attracted much attention in the field of natural language processing, owing to its high performance in language understanding-related tasks.

Situated GAIL: Multitask imitation using task-conditioned adversarial inverse reinforcement learning

no code implementations • 1 Nov 2019 • Kyoichiro Kobayashi, Takato Horii, Ryo Iwaki, Yukie Nagai, Minoru Asada

This study proposes an extended framework called situated GAIL (S-GAIL), in which a task variable is introduced to both the discriminator and generator of the GAIL framework.

Imitation Learning reinforcement-learning +1

Neuro-SERKET: Development of Integrative Cognitive System through the Composition of Deep Probabilistic Generative Models

no code implementations • 20 Oct 2019 • Tadahiro Taniguchi, Tomoaki Nakamura, Masahiro Suzuki, Ryo Kuniyasu, Kaede Hayashi, Akira Taniguchi, Takato Horii, Takayuki Nagai

The model is called VAE+GMM+LDA+ASR.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Deep Emotion: A Computational Model of Emotion Using Deep Neural Networks

no code implementations • 25 Aug 2018 • Chie Hieida, Takato Horii, Takayuki Nagai

In this study, a model of emotions is proposed to elucidate the mechanism of emotions through the computational model.

Decision Making