Undistorted raw LiDAR scans and static point extractions method for ground truth static scene sparse flow generation
AssigneeTusimple, Inc.
InventorsYi Wang, Yi Luo, Wentao Zhu, Panqu Wang
Life of this patent
Estimating the term…
Abstract
A method of generating a ground truth dataset for motion planning of a vehicle is disclosed. The method includes: obtaining undistorted LiDAR scans; identifying, for a pair of undistorted LiDAR scans, points belonging to a static object in an environment; aligning the close points based on pose estimates; and transforming a reference scan that is close in time to a target undistorted LiDAR scan so as to align the reference scan with the target undistorted LiDAR scan.
Claims33
A method of generating a ground truth dataset for motion planning for a non-transitory computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, causes the computing device to perform the following steps comprising:
- transforming LiDAR scans into undistorted LiDAR scans based on LiDAR's poses for the motion planning of a vehicle;
- identifying, for a pair of undistorted LiDAR scans, points belonging to a static object in an environment;
- aligning the close points based on pose estimates;
- and
- transforming a reference scan that is close in time to a target undistorted LiDAR scan so as to align the reference scan with the target undistorted LiDAR scan.
A system for generating a ground truth dataset for motion planning, the system comprising:
- an internet server, comprising:
- an I/O port, configured to transmit and receive electrical signals to and from a client device;
- a memory;
- one or more processing units;
- and
- one or more programs stored in the memory and configured for execution by the one or more processing units, the one or more programs including instructions for:
- a collecting module configured to collect LiDAR scans for the motion planning of a vehicle;
- a detecting module configured to detect two pose estimates that are closest to LiDAR scan accusation time;
- a determining module configured to determine LiDAR's poses by interpolating the two pose estimates;
- and
- a transforming module configured to transform the LiDAR scans into undistorted LiDAR scans based on the LiDAR's poses.
A system having a non-transitory computer readable storage medium storing one or more programs, the one or more programs comprising instructions which, when executed by the one or more processors of a computing device, cause the computing device to:
- collect LiDAR scans for a motion planning of a vehicle;
- detect two pose estimates that are closest to LiDAR scan accusation time;
- determine LiDAR's poses by interpolating the two pose estimates;
- and
- transform the LiDAR scans into undistorted LiDAR scans based on the LiDAR's poses.
A method of generating a ground truth dataset for motion planning for a non-transitory computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computing device, causes the computing device to perform the following steps comprising:
- collecting LiDAR scans for the motion planning of a vehicle;
- detecting two pose estimates that are closest to LiDAR scan accusation time;
- determining LiDAR's poses by linearly interpolating the two GNSS-inertial pose estimates that are closest to LiDAR scan accusation time;
- and
- transforming the LiDAR scans into undistorted LiDAR scans based on the LiDAR's poses.
Dependencies are inferred from the claim text.