Naver had 14 patents in robotics during Q4 2023. The patent filed by Naver Corp in Q4 2023 describes a navigating device that uses a camera to capture images of scenes with humans, a feature module to generate vectors summarizing human movement, a policy module to generate navigation actions based on these vectors, and a propulsion control module to control the device’s movement based on the generated actions. GlobalData’s report on Naver gives a 360-degreee view of the company including its patenting strategy. Buy the report here.
Smarter leaders trust GlobalData
Naver grant share with robotics as a theme is 7% in Q4 2023. Grant share is based on the ratio of number of grants to total number of patents.
Recent Patents
Application: Distilling information for crowd-aware robot navigation (Patent ID: US20230359212A1)
The patent filed by Naver Corp. describes a navigating device that includes a camera capturing images of scenes with humans, a feature module generating feature vectors summarizing human movement, a policy module generating navigation actions based on the feature vectors, and a propulsion control module controlling the device's movement based on the actions. The device can be a robot or autonomous vehicle, with the policy module trained using reinforcement learning and the feature module trained using supervised learning without explicit human positions.
The navigating robot described in the patent utilizes a camera, feature module, policy module, and propulsion control module to navigate scenes with humans. The policy module is trained jointly with an encoder module using reinforcement learning, while the feature module is trained using supervised learning based on training data that excludes human positions. The feature module includes components like a CNN module, flattening module, attention module, and MLP module to generate feature vectors, and the robot does not use LIDAR sensors. The training system outlined in the patent involves a dataset with privileged and non-privileged training samples, training the encoder and policy modules using reinforcement learning, and then training the feature module using supervised learning with non-privileged samples. The system uses a PPO algorithm for training and includes detections of humans in the training data.
To know more about GlobalData’s detailed insights on Naver, buy the report here.
Premium 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.
