18178725. SYSTEMS AND METHODS FOR PLANNING A TRAJECTORY OF AN AUTONOMOUS VEHICLE BASED ON ONE OR MORE OBSTACLES simplified abstract (Kodiak Robotics, Inc.)
SYSTEMS AND METHODS FOR PLANNING A TRAJECTORY OF AN AUTONOMOUS VEHICLE BASED ON ONE OR MORE OBSTACLES
Organization Name
Inventor(s)
Yinsen Jia of New York NY (US)
Abhyuday Puri of New York NY (US)
SYSTEMS AND METHODS FOR PLANNING A TRAJECTORY OF AN AUTONOMOUS VEHICLE BASED ON ONE OR MORE OBSTACLES - A simplified explanation of the abstract
This abstract first appeared for US patent application 18178725 titled 'SYSTEMS AND METHODS FOR PLANNING A TRAJECTORY OF AN AUTONOMOUS VEHICLE BASED ON ONE OR MORE OBSTACLES
Simplified Explanation: The patent application describes systems and methods for planning a vehicle's trajectory based on obstacles detected by sensors, such as LiDAR. The method involves generating data points, detecting obstacles, labeling them based on collidability, and planning a safe trajectory for the vehicle.
Key Features and Innovation:
- Utilizes sensors to detect obstacles in a vehicle's path
- Projects LiDAR data into images for obstacle analysis
- Labels obstacles based on collidability for trajectory planning
Potential Applications: This technology can be applied in autonomous vehicles, drones, and robotics for obstacle avoidance and path planning.
Problems Solved: Addresses the challenge of safely navigating vehicles in complex environments with obstacles.
Benefits:
- Enhances safety by identifying and avoiding obstacles
- Improves efficiency in trajectory planning for vehicles
- Enables autonomous vehicles to navigate challenging environments
Commercial Applications: Potential commercial applications include autonomous vehicles, drone delivery services, and industrial robotics for enhanced navigation and safety.
Prior Art: Prior art related to this technology may include research on LiDAR-based obstacle detection and trajectory planning in autonomous vehicles.
Frequently Updated Research: Stay updated on advancements in LiDAR technology, obstacle detection algorithms, and autonomous vehicle navigation systems for relevant research.
Questions about Trajectory Planning Technology: 1. How does this technology improve vehicle safety in complex environments? 2. What are the key factors considered in planning a trajectory based on obstacle detection?
Original Abstract Submitted
Systems and methods for planning a trajectory of a vehicle based on one or more obstacles is provided. The method may comprise generating one or more data points from one or more sensors coupled to a vehicle, and, using a processor, detecting one or more obstacles within a LiDAR point cloud, generating a patch for each of the one or more obstacles, projecting the LiDAR point cloud into the image, wherein each patch represents a region of an image for each of the one or more obstacles, performing a factor query on the image for each of the one or more obstacles, for each of the one or more obstacles, based on the factor query, determining a label for the obstacle and labeling the obstacle with the label, and planning a trajectory of the vehicle. The label may indicate a collidability of the obstacle.