Denso had 20 patents in robotics during Q3 2023. The first patent is for a system that controls a robot arm to pour fluid from one container to another. It uses machine learning to generate a learning model based on time-series information of the robot arm’s posture and the weight of the second container. The learning model takes input of the robot arm’s posture and the weight of the second container at a first time and outputs the posture of the robot arm at a second time.

2. The second patent is for a system that produces a data set to train a neural network for object detection. It uses a ranging sensor system to determine a first set of objects and another object detection system to determine a second set of objects. The system compares the counts of objects in both sets and designates the set with a different count as the data set to train the neural network.

3. The third patent is for a primary-and-secondary robot system. It includes a primary robot whose posture can be changed by external force and a secondary robot whose posture is controlled to be the same as the primary robot. A control unit ensures that the posture of the primary robot matches the posture of the secondary robot and limits the acceleration rate of the primary robot’s movement.

4. The fourth patent is for a vehicle control method in case of a disaster. If the vehicle detects a disaster and determines that it is on a different floor from the priority evacuation place, it sets a destination to a second evacuation place on the same floor and moves the vehicle there. GlobalData’s report on Denso gives a 360-degreee view of the company including its patenting strategy. Buy the report here.

Smarter leaders trust GlobalData

Report-cover

Premium Insights Denso Corp - Company Profile

Buy the Report

Premium Insights

The gold standard of business intelligence.

Find out more

Denso grant share with robotics as a theme is 45% in Q3 2023. Grant share is based on the ratio of number of grants to total number of patents.

Recent Patents

Application: Method of generating a learning model for transferring fluid from one container to another by controlling robot arm based on a machine-learned learning model, and a method and system for weighing the fluid (Patent ID: US20230271319A1)

The patent filed by Denso Corp. describes a system for controlling a robot arm to pour fluid from one container to another. The system utilizes machine learning to generate a learning model based on time-series information of the robot arm's posture and the changing weight of the second container. The learning model takes as input the posture of the robot arm and the weight of the second container at a first time and outputs the posture of the robot arm at a second time. The learning data used to generate the model includes information showing the load acting on the robot arm, such as the current values of motors in the robot arm's axes.

The patent also describes methods for generating learning data, inferring the posture of the robot arm, and weighing a target fluid. These methods involve acquiring information about the robot arm's posture and the weight of the second container at a first time and inputting this information to a learning model for machine learning. The learning model has been trained using learning data that includes the posture and weight information at the first time and outputs the posture information at a second time. The movements of the robot arm are controlled based on the posture information at the second time.

Furthermore, the patent describes a system for weighing a target fluid that includes a first state data acquiring unit to acquire information about the robot arm's posture, a second state data acquiring unit to acquire the weight of the second container, a learning processing unit to input the posture and weight information at the first time to the learning model, and a control unit to control the movements of the robot arm based on the posture information at the second time.

Overall, the patent filed by Denso Corp. presents a system and methods for controlling a robot arm to pour fluid from one container to another using machine learning. The system utilizes learning models generated from time-series information of the robot arm's posture and the changing weight of the second container. The movements of the robot arm are controlled based on the output of the learning model, allowing for accurate and efficient fluid pouring operations.

To know more about GlobalData’s detailed insights on Denso, 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

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.