18064083. USING STATIC GRID MAP TO CROSS-CHECK DYNAMIC OBJECTS simplified abstract (Robert Bosch GmbH)
Contents
USING STATIC GRID MAP TO CROSS-CHECK DYNAMIC OBJECTS
Organization Name
Inventor(s)
Oliver F. Schwindt of Sunnyvale CA (US)
Stephan Reuter of Bavaria (DE)
Christos Zalidis of Mountain View CA (US)
Tobias Berling of Sunnyvale CA (US)
USING STATIC GRID MAP TO CROSS-CHECK DYNAMIC OBJECTS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18064083 titled 'USING STATIC GRID MAP TO CROSS-CHECK DYNAMIC OBJECTS
Simplified Explanation: The patent application describes systems and methods for controlling an autonomous vehicle by detecting dynamic objects in the environment and determining their existence probability.
- The system includes an electronic processor and a sensor to detect dynamic objects.
- The processor generates a dynamic object list with information about the detected objects.
- It overlays this information on a static occupancy grid with occupancy probabilities of static objects.
- By comparing the dynamic and static objects, it calculates the existence probability of the dynamic object.
- The system can classify the dynamic object as a "ghost object" based on this probability.
Key Features and Innovation:
- Detection and classification of dynamic objects in the environment.
- Calculation of dynamic object existence probability based on overlap with static objects.
- Classification of dynamic objects as "ghost objects" based on their existence probability.
Potential Applications: This technology can be applied in autonomous vehicles, robotics, and surveillance systems for improved object detection and classification.
Problems Solved:
- Enhanced detection and classification of dynamic objects.
- Improved decision-making for autonomous vehicles in dynamic environments.
Benefits:
- Increased safety and efficiency in autonomous vehicle operations.
- Better understanding of the environment for autonomous systems.
Commercial Applications: The technology can be utilized in autonomous vehicles, industrial automation, security systems, and smart city infrastructure for enhanced object detection and classification.
Prior Art: Prior research in object detection and classification systems for autonomous vehicles and robotics can provide insights into similar technologies.
Frequently Updated Research: Stay informed about advancements in object detection algorithms, sensor technologies, and autonomous vehicle systems for potential improvements in this technology.
Questions about Autonomous Vehicle Control: 1. How does the system determine the existence probability of dynamic objects? 2. What are the potential challenges in implementing this technology in real-world autonomous vehicle systems?
Original Abstract Submitted
Systems and methods for controlling an autonomous vehicle. One system includes an electronic processor and a sensor configured to detect a dynamic object in an environment. The electronic processor is configured to generate a dynamic object list including dynamic object information associated with the detected dynamic object. The electronic processor is also configured to receive a static occupancy grid including a plurality of cells storing occupancy information and occupancy probabilities associated with a static object in the environment. The electronic processor is further configured to superimpose the dynamic object information on the static occupancy grid, determine an overlap of the detected dynamic object and the static object, determine a dynamic object existence probability associated with the detected dynamic object based on the overlap, and classify the detected dynamic object as a ghost object based on the dynamic object existence probability.
