Generation of Optimal Coverage Paths for Mobile Robots Using Hybrid Genetic Algorithm

This paper presents new optimal offline approaches to solve the coverage path planning problem. A novel hybrid genetic algorithm (HGA), which uses, the turn-away starting point and backtracking spiral algorithms for performing local search, is proposed for grid-based environmental representations. The HGA algorithm is validated using the following three different fitness functions: the number of cell visits, traveling time, and a new energy fitness function based on experimentally acquired energy values of fundamental motions. Computational results show that compared to conventional methods, HGA improves paths up to 38.4%; moreover, HGAs have a consistent fitness for different starting positions in an environment. Furthermore, experimental results prove the validity of the fitness function.

Automatic Generation of Multidestination Routes for Autonomous Wheelchairs

To solve the problem of autonomously navigating multiple destinations, which is one of the tasks in the Tsukuba Challenge 2019, this paper proposes a method for automatically generating the optimal travel route based on costs associated with routes. In the proposed method, the route information is generated by playing back the acquired driving data to perform self-localization, and the self-localization log is stored. In addition, the image group of road surfaces is acquired from the driving data. The costs of routes are generated based on texture analysis of the road surface image group and analysis of the self-localization log. The cost-added route information is generated by combining the costs calculated by the two methods, and by assigning the combined costs to the route. The minimum-cost multidestination route is generated by conducting a route search using cost-added route information. Then, we evaluated the proposed method by comparing it with the method of generating the route using only the distance cost. The results confirmed that the proposed method generates travel routes that account for safety when the autonomous wheelchair is being driven.

Path Planning Design for Boarding-Type Personal Mobility Unit Passing Pedestrians Based on Pedestrian Behavior

In this study, we consider a scenario in which a boarding-type personal mobility (BPM) unit navigates in a mixed environment with pedestrians. The BPM unit passenger is expected to pass pedestrians in a smooth manner without imparting anxiety to them. This is accomplished by selecting appropriate paths on a successively updated map of the surrounding environment. Based on a model that simulates a pedestrian’s path selection behavior, we design and investigate a path selection method that avoids sudden behavior changes in the BPM unit, which may cause apprehensiveness to the passenger.