Hyundai Motor has been granted a patent for a method that generates intermediate waypoints for a robot’s navigation system. The method involves receiving a navigation route with high-level waypoints based on static obstacle data, receiving image data from an image sensor, generating intermediate waypoints based on the image data, and adding them to the navigation route. The robot then navigates from the starting location to the destination using the high-level waypoints and intermediate waypoints. GlobalData’s report on Hyundai Motor gives a 360-degree view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
According to GlobalData’s company profile on Hyundai Motor, battery management systems was a key innovation area identified from patents. Hyundai Motor's grant share as of September 2023 was 47%. Grant share is based on the ratio of number of grants to total number of patents.
Generating intermediate waypoints for robot navigation based on image data
A recently granted patent (Publication Number: US11774247B2) describes a computer-implemented method and a robot that can navigate through an environment using image data and obstacle maps. The method involves receiving image data of the environment from an image sensor and a body obstacle map that identifies areas the robot cannot traverse. Based on this information, a sparse graph is generated, representing possible paths for the robot. A coarse path is planned from the starting location to the destination, and an intermediate waypoint is generated along this path where the line of sight by the image sensor is lost. The robot then navigates from the starting location to the destination, passing through the intermediate waypoint.
The method further includes generating a full configuration space map based on the body obstacle map, which represents the environment as a two-dimensional grid with elements representing different spaces. Each element of the full configuration space map includes a set of yaw configurations, classifying them as valid or invalid based on whether they are safe from obstacles. From this map, a compressed configuration space map is generated, categorizing elements as yaw collision zones, yaw free zones, or yaw constrained zones. A dense graph is generated from the compressed configuration space map, consisting of elements categorized as yaw free zones. The sparse graph is then combined with the dense graph to create a final graph, on which an A* search algorithm is executed.
The robot described in the patent includes a body, legs for maneuvering, data processing hardware, and memory hardware. The robot receives image data and a body obstacle map, generates a sparse graph, plans a coarse path, determines an intermediate waypoint, and navigates towards the destination using the same method as described above.
This patent introduces a method and robot that can effectively navigate through an environment by utilizing image data, obstacle maps, and graph-based planning techniques. By incorporating the concept of line of sight and generating intermediate waypoints, the robot can adapt its path to avoid obstacles and ensure efficient navigation. The use of configuration space maps and graph generation techniques further enhances the robot's ability to plan and execute its movements. This technology has the potential to be applied in various fields, such as autonomous robots, drones, and self-driving vehicles, to improve their navigation capabilities in complex environments.
To know more about GlobalData’s detailed insights on Hyundai Motor, buy the report here.
Data Insights
From
The gold standard of business intelligence.
Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.
GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.
GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.
