Yusuke Fukazawa

Cooperative exploration of mobile robots using reaction-diffusion equation on a graph

In this paper, we propose cooperative exploration method for mobile robots in a working area. The method will generate and share the minimal-cost path for each mobile robot. Each mobile robot goes through several observation points to accomplish the exploration. The observation points should be arranged at a fixed distance from at least on corresponding observation point. In addition, the number of observation points and the lengths of paths for each mobile robot are to be minimized. The proposed method should have the efficiency in computational cost concurrently with the adaptability to dynamic environmental changes.

Region exploration path planning for a mobile robot expressing working environment by grid points

In this paper, region exploration path planning algorithm is proposed. In order for a mobile robot to perform this task, appropriate measures with the shape of the working environment, which may be intricate or curved, is necessary. In addition, a robot must be able to react and be flexible when confronted with obstacles. With this algorithm, these challenges can be met by approximately expressing the working environment in grid points and regenerating the path using one that was planned beforehand. Simulations are used to demonstrate proposed exploration path planning and re-planning algorithm.

Controlling a mobile robot that searches for and rearranges objects with unknown locations and shapes

This paper offers a proposal for an algorithm of controlling a mobile robot that searches for and rearranges objects with unknown locations and shape. In this paper, we divide the task into two parts: exploration task and rearrangement task. The algorithms for each part of the task are presented with respect to the effectiveness of the path length and computational cost. Additionally integration algorithm that effectively combines exploration and rearrangement is presented. Experiments with a real robot are conducted to demonstrate the effectiveness of the proposed algorithm.

Extraction of onomatopoeia used for foods from food reviews and its application to restaurant search

Onomatopoeia is widely used in food reviews about food or restaurants. In this paper, we propose and evaluate a method to extract onomatopoeia including unknown ones automatically from food reviews sites. From the evaluation result, we found that we can extract onomatopoeia for specific foods with more than 46% precision; we find 18 unknown onomatopoeia, i.e. not registered in an existing onomatopoeia dictionary, in 62 extracted onomatopoeia. In addition, we propose a system that can present the user with a list of onomatopoeia specific to a restaurant she is interested in. The evaluation results indicate that an intuitive restaurant search can be done via a list of onomatopoeia, and that they are helpful for selecting food or restaurants.

Exploration-path generation of multiple mobile robots using reaction-diffusion equation on a graph

In this paper we present a method for cooperative exploration by multiple mobile robots in a restricted working area. By generating and sharing the minimal-length path for each mobile robot in which mobile robots go through several observation points to explore the working area. The observation points should be arranged at a fixed distance from at least one corresponding observation point. Therefore, mobile robots can obtain the complete information of the working area by only moving along all of the observation points. To reduce the redundancy of exploration task, the number of observation points and the length of observation paths for each mobile robot are to be minimized. To ensure the advantages from using multiple mobile robots, exploration path must be equally assigned to each mobile robot. Simulations had proved the efficiency of cooperating mobile robots using our proposed method. The feasible of our method is real world with actual mobile robots was demonstrated in cooperative exploration experiment.

Real-Time Cooperative Exploration by Reaction-Diffusion Equation on a Graph

In this paper we present a path planning method for the environment exploration using the reaction-diffusion equation on a graph. We autonomously arrange sub-goals for robots to go along and explore the environment. By using reaction-diffusion on a graph for sub-goals arrangement, we can deal with the emergence of unknown objects or obstacles in the dynamic environment. This method also can explore the environment in real-time and make sure that robots completely explore all the area in the environment. The results given in this paper demonstrate that our method successfully solves exploration problems both in simulations and in real robot experiments.

Acquisition of intermediate goals for an agent executing multiple tasks

In this paper, an algorithm that acquires the intermediate goals between the initial and goal states is proposed for an agent executing multiple tasks. We demonstrate the algorithm in the problem of rearranging multiple objects. The result shows that the moving distance to transfer the entire objects to their goal configuration is 1/15 of that without using intermediate goals. We experiment using a real robot to confirm that the intermediate goal can be adapted to a real environment. Our experimental results showed that an agent could adapt the intermediate goals, which were acquired in the simulation, to the experimental environment

Cooperative exploration path planning for mobile robots by reaction-diffusion equation on graph

In this paper, an exploration path algorithm is proposed for mobile robots to make a map of a working environment. The exploration task is defined as a problem of generating minimal-cost path, in which robots go through several observation points and observe a working environment. Both number of the observation points and path length should be minimized. The proposed algorithm has two characteristics: efficiency in exploration and adaptability to dynamic environmental changes. Our method can be realized with the combination of (a) distribution of observation points by a reaction-diffusion equation on a graph, and (b) generation of a Hamiltonian circle that connects all observation points. The observation points dynamically change their arrangements in accordance with the recognized environmental situation. The calculation cost for exploration path generation is shown to be in order of N/sup 1.5/, where N is the number of the observation points. Our method can be extended into cooperative exploration path planning method. Our method homogenized the arrangement of the observation points, then only a basic partition method can equally part exploration task for each robot. The effectiveness of our method is shown by both simulation and real robot experiments.

Realizing the exploration and rearrangement of multiple unknown objects by an actual mobile robot

This paper offers a proposal for realizing the exploration and rearrangement of multiple unknown objects that lay scattered in working environments. The objective of the exploration task is to find all the objects in the environments. On the other hand, the objective of the rearrangement task is to carry all the objects to their goal position. Many applications are possible if the exploration and rearrangement tasks are combined. Some of them are cleaning, mine detecting and housework. An algorithm that integrates two tasks is presented with respect to the effectiveness of the path length and computational cost. In addition, an exploration algorithm is proposed that can work well in an environment that has many objects. In order to verify the algorithm, experiments are conducted with an actual robot. In the experimentals, an environmental recognition method is developed by attaching a mark to the objects. The robot recognizes the objects by finding the mark. It then obtains information from the mark. The mark is also used to modify the odometry error of the robot by computing its configuration relative to a mark attached to a wall. The success rate of this experiment was almost 80% in 20 trials.

Discovering pattern of onomatopoeia used in food reviews

In this paper, we investigated onomatopoeia usage pattern in food reviews by proposing LDA (Latent Dirichlet Allocation) based onomatopoeia usage pattern analysis model. We collected total 685 numbers of onomatopoeias which are distributed to 208 food categories from 3,581,808 food reviews of Japanese food review site Tabelog. From the experimental result, we found several patterns how the onomatopoeias are chosen. The onomatopoeia is chosen based on users interest on the combination of {location of food, material of the food, cooking method} and {the texture of food, sound when eating, and looks of food peoples status when eating the food}. In addition, we investigate how the precision of the clustering result changes depending on the N (number of onomatopoeia of each food categories). We found that the results of N=30 is better than one of N=100 as large number of onomatopoeia for each food categories like 100 is likely to include onomatopoeias that are irrelevant to food.