17849034. SYSTEMS AND METHODS FOR DETECTING ERRONEOUS LIDAR DATA simplified abstract (TOYOTA JIDOSHA KABUSHIKI KAISHA)
SYSTEMS AND METHODS FOR DETECTING ERRONEOUS LIDAR DATA
Organization Name
TOYOTA JIDOSHA KABUSHIKI KAISHA
Inventor(s)
Rohit Gupta of Santa Clara CA (US)
Roger D. Melen of Los Altos Hills CA (US)
SYSTEMS AND METHODS FOR DETECTING ERRONEOUS LIDAR DATA - A simplified explanation of the abstract
This abstract first appeared for US patent application 17849034 titled 'SYSTEMS AND METHODS FOR DETECTING ERRONEOUS LIDAR DATA
Simplified Explanation
The patent application describes techniques for detecting erroneous LIDAR data. LIDAR point-cloud data and image data are received and processed to measure the spatial correspondence between them. If the spatial correspondence fails to meet certain criteria, the LIDAR data is identified as erroneous. Otherwise, the LIDAR data is considered valid and used to control the operation of a robot.
- Techniques for detecting erroneous LIDAR data are disclosed.
- LIDAR point-cloud data and image data are received and processed.
- Segmented optical-flow data is generated from the image data.
- A 2D grid is used to fuse LIDAR points and optical-flow pixels.
- A hash function generates a 1D hash table and an associated index for the fused objects.
- Queries are performed using the hash table and index to measure spatial correspondence.
- Erroneous LIDAR data is identified if the spatial correspondence fails to meet predetermined criteria.
- Valid LIDAR data is used to control the operation of a robot.
Potential Applications
- Robotics and autonomous vehicles
- Environmental mapping and monitoring
- Object detection and tracking
Problems Solved
- Detection of erroneous LIDAR data
- Improving the accuracy and reliability of LIDAR-based systems
- Ensuring the safety and efficiency of robotic operations
Benefits
- Enhanced data quality and reliability
- Improved decision-making and control for robots
- Increased safety and efficiency in various applications
Original Abstract Submitted
Techniques for detecting erroneous LIDAR data are disclosed herein. One embodiment receives LIDAR point-cloud data pertaining to a robot's environment; receives image data and generates segmented optical-flow data therefrom; fuses, in a 2D grid, a plurality of objects including LIDAR points and optical-flow pixels; executes a hash function that generates, for the plurality of objects, a 1D hash table and an associated index; performs one or more queries using the 1D hash table and the associated index to measure the extent of spatial correspondence between the LIDAR points and the optical-flow pixels; identifies the LIDAR point-cloud data as erroneous, when the extent of spatial correspondence fails to satisfy one or more predetermined criteria; and identifies the LIDAR point-cloud data as valid and controls operation of the robot based, at least in part, on the LIDAR point-cloud data, when the extent of spatial correspondence satisfies the one or more predetermined criteria.
