Dji Research LLC

Sz Dji Technology Co., Ltd.

Dji Technology, Inc.

Arjun Sukumar Menon

Weifeng Liu

Arnaud Thiercelin

Rohit Sant

Alain Pimentel

Kalyani Premji Nirmal

Comran Morshed

Yucheng Liu

Feng Cao

Junli Liu

Zhenghe Shangguan

Zhenyu Yang

Jifei Xu

Joshua Acosta

Fernando Pablo Quevedo

Techniques are disclosed for mapping in a movable object environment. A system may comprise a movable object, a payload coupled to the movable object, the payload comprising an embedded system including an embedded processor, a scanning sensor, one or more cameras, and an inertial navigation system (INS). The payload further including an online processing application, the online processing application including instructions which, when executed by the embedded processor, cause the online processing application to obtain mapping data from the scanning sensor, obtain image data from a camera of the one or more cameras, obtain positioning data from the INS, associate the mapping data with the positioning data to generate georeferenced data, downsample the georeferenced data to generate downsampled georeferenced data, and provide the downsampled georeferenced data to a client device to be visualized on the client device in real-time.

Online point cloud processing of LIDAR and camera data

Techniques are disclosed for real-time mapping in a movable object environment. A real-time mapping system can include at least an unmanned aerial vehicle (UAV), comprising a propulsion system, a main body coupled to the propulsion system and a payload assembly coupled to the main body via a payload port, wherein the payload assembly is configured to couple to the payload port and support a scanning sensor and a positioning sensor.

Movable object performing real-time mapping using a payload assembly

Techniques are disclosed for post-processing mapping data in a movable object environment. A method for post-processing mapping data can include obtaining a plurality of scans, each scan comprising georeferenced mapping data and corresponding payload pose data obtained from a payload supported by an unmanned aerial vehicle (UAV), generating a plurality of local maps based on matching portions of the plurality of scans using the georeferenced mapping data, generating a pose graph based on identifying a plurality of correspondence points among the plurality of local maps, and optimizing the pose graph by minimizing an error distance between each pair of correspondence points to obtain optimized transforms for two scans among the plurality of the scans.

Post-processing of mapping data for improved accuracy and noise-reduction

Techniques are disclosed for performing custom waypoint missions using an onboard computing device in communication with a movable object. The movable object can include a flight controller, and a communication system. The flight controller can be in communication with the onboard computing device which includes a processor and an onboard data manager. The onboard data manager can receive at least one input, determine one or more instructions to be performed by the at least one movable object based on the at least one input, generate movement commands to implement the one or more instructions, and send movement commands to the flight controller to be executed.

Customizable waypoint missions

Techniques are disclosed for real-time mapping in a movable object environment. A system for real-time mapping in a movable object environment, may include at least one movable object including a computing device, a scanning sensor electronically coupled to the computing device, and a positioning sensor electronically coupled to the computing device. The system may further include a client device in communication with the at least one movable object, the client device including a visualization application which is configured to receive point cloud data from the scanning sensor and position data from the positioning sensor, record the point cloud data and the position data to a storage location, generate a real-time visualization of the point cloud data and the position data as it is received, and display the real-time visualization using a user interface provided by the visualization application.

User interface for displaying point clouds generated by a LiDAR device on a UAV

User interface for displaying point clouds generated by a lidar device on a UAV

Growing community of inventors

San Jose, CA, United States of America

Arjun Sukumar Menon