HAMT 2020 Abstracts

Short Papers
Short Papers
Paper Nr: 2
Title:

Human-agents Interactions in Multi-Agent Systems: A Case Study of Human-UAVs Team for Forest Fire Lookouts
Authors:

Sagir M. Yusuf and Chris Baber
Abstract: In this paper, we propose an architecture that uses predictions tools obtained via Bayesian learning algorithms to monitor the issues of communication, fault tolerance, and adaptation in human-agent mission. The architecture describes different level of knowledge, planning, and commands differ by their priorities. We tested the model using forest fire lookouts problem on a simulation platform (AMASE). The process uses the conjugate gradient descent algorithm to perform the Bayesian Belief Network training. The output of the training process is a well-trained BBN for agents’ prediction, estimation, and decision making during communication failure. The prediction perfection of the human and agents were compared and studied. Although results proof that human approach is prone to error but is good in terms of emergency commands execution. We suggested that the use of a well-trained prediction tool (i.e., the output BBN) could be used in monitoring mission during communication link, hardware, or software breakdown.
Download
Paper Nr: 3
Title:

A User Independent Method for Identifying Hand Gestures with sEMG
Authors:

Hitoshi Tamura, Kazuki Itou and Yasushi Kambayashi
Abstract: We propose a method to determine hand gestures using sEMG (surface Electromyogram) measured from the forearm. The detection method uses the LSTM (Long Short Term Memory) model of RNN (Recurrent Neural Network). Although the conventional method requires the learning data of the user, this is a method that an unspecified number of users can use immediately by enhancing the data. We have confirmed that the accuracy does not change even if the mounting position of the sensor is shifted. We have shown the effectiveness of the data enhancement by numerical experiments.
Download
Paper Nr: 6
Title:

Development of Agents that Create Melodies based on Estimating Gaussian Functions in the Pitch Space of Consonance
Authors:

Hidefumi Ohmura, Takuro Shibayama, Keiji Hirata and Satoshi Tojo
Abstract: Music is organized by simple physical structures, such as the relationship between the frequencies of tones. We have focused on the frequency ratio between notes and have proposed lattice spaces, which express the ratios of pitches and pulses. Agents produce melodies using distributions in the lattice spaces. In this study, we upgrade the system to analyze existing music. Therefore, the system can obtain the distribution of the pitch in the pitch lattice space and create melodies. We confirm that the system fits the musical features, such as modes and scales of the existing music as GMM. The probability density function in the pitch lattice space is suggested to be suitable for expressing the primitive musical structure of the pitch. However, there are a few challenges of not adapting a 12-equal temperament and dynamic variation of the mode; in this study, we focus on these challenges.
Download
Paper Nr: 7
Title:

Capture of Multi Intruders by Cooperative Multiple Robots using Mobile Agents
Authors:

Tadashi Shoji, Munehiro Takimoto and Yasushi Kambayashi
Abstract: Detecting and capturing intruders are two of the most important function of multi-robot systems. In this paper, we propose an effective approach to capture agile intruders with not-so-agile mobile robots. In general, it is difficult to drive several robots to pursue moving objects while adjusting their behaviors. We make mobile robots cooperate using two mobile software agents that control the mobile robots. The mobile software agents migrate from one robot to another robot that is located at much suitable positions for guiding moving robots to the target location. This control manner contributes to not only reduction of movement cost of the mobile robots, but also their efficient movement without interference from other robots. We have implemented a simulator, on which we demonstrated effectiveness of our control manner for intruders-capturing system.
Download
Paper Nr: 8
Title:

Human-agent Explainability: An Experimental Case Study on the Filtering of Explanations
Authors:

Yazan Mualla, Igor H. Tchappi, Amro Najjar, Timotheus Kampik, Stéphane Galland and Christophe Nicolle
Abstract: The communication between robots/agents and humans is a challenge, since humans are typically not capable of understanding the agent’s state of mind. To overcome this challenge, this paper relies on recent advances in the domain of eXplainable Artificial Intelligence (XAI) to trace the decisions of the agents, increase the human’s understandability of the agents’ behavior, and hence improve efficiency and user satisfaction. In particular, we propose a Human-Agent EXplainability Architecture (HAEXA) to model human-agent explainability. HAEXA filters the explanations provided by the agents to the human user to reduce the user’s cognitive load. To evaluate HAEXA, a human-computer interaction experiment is conducted, where participants watch an agent-based simulation of aerial package delivery and fill in a questionnaire that collects their responses. The questionnaire is built according to XAI metrics as established in the literature. The significance of the results is verified using Mann-Whitney U tests. The results show that the explanations increase the understandability of the simulation by human users. However, too many details in the explanations overwhelm them; hence, in many scenarios, it is preferable to filter the explanations.
Download