Keisuke Nakamura

TL;DR: This paper proposes a model-based method-IRL-TAMER-by combining learning from demonstration via inverse reinforcement learning (IRL) and learning from human reward via the TAMER framework and suggests that although an agent learning via IRL can learn a useful value function indicating which states are good based on the demonstration, it cannot obtain an effective policy navigating to the goal state with one demonstration.

TL;DR: A sound processing apparatus includes a sound collection position calculating unit configured to calculate sound collection positions of sound signals of multiple channels on the basis of the sound signals, a sound source direction calculating unit configuring to calculate a sound sources direction on a sound signal of the multiple channels, and a second transfer function calculating unit that interpolates the first transfer function corresponding to each of a plurality of sound source directions.

TL;DR: The use of the algorithms designed for contact PPG on remote PPG signals can lead to respiratory rate estimations with a mean absolute error below 3 breaths-per-minute, benchmarked using this standard and some other metrics to interpret the quality of the assessment.

TL;DR: The experimental results showed that the proposed framework successfully calibrated an eight-channel asynchronous microphone array both in a simulated and a real environment even when system parameters such as variances are set to be 10 times larger than the optimal values.

TL;DR: In this paper, the authors proposed a production instruction method to enable a robot and an operator to produce an assembly finished product by sharing an assembly operation to assemble components into a product in the order of process in one production cell as a working place in a cell production system.