Layered Costmap Sharing for Vehicular Network Perception
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current Collective Perception Service (CPS) solutions for Intelligent Transport Systems (ITS) face inefficiencies in sharing perception information, particularly in scenarios with a large number of objects or occlusions, leading to high communication overhead and computational resource consumption.
Innovation Solution
The implementation of layered costmaps and efficient message exchange mechanisms, including partial/incremental Collective Perception Message (CPM) transmission and group reporting of objects, to reduce signaling overhead and improve costmap quality among ITS stations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If traditional Collective Perception Service solutions share perception information in scenarios with a large number of objects or occlusions, then the completeness of perception information is improved, but the communication overhead and computational resource consumption increase significantly
Solution Approach 1:
The patent segments the perception information sharing process by introducing layered costmaps that divide the environment representation into multiple layers (e.g., static objects, dynamic objects, occluded regions). This segmentation allows selective sharing of only necessary costmap layers rather than transmitting complete perception data for all objects, thereby reducing communication overhead while maintaining information completeness for critical elements.
Solution Approach 2:
The patent extracts and transmits only the essential costmap data required for collective perception rather than sharing all raw sensor data or complete object lists. By extracting key environmental features and representing them through compact costmap layers, the system reduces the volume of transmitted information while preserving the necessary perception completeness for safety-critical applications.
2Measurement precision
If traditional CPS solutions transmit complete perception data for all objects, then the accuracy of environmental perception is improved, but the signaling overhead increases
Solution Approach 1:
The patent changes the representation parameters by transforming raw perception data into costmap format with discrete cost values (e.g., 0-255 scale representing different levels of occupancy or risk). This parameter transformation compresses the data representation while maintaining the essential accuracy information needed for environmental perception, thereby reducing signaling overhead without sacrificing measurement precision.
Solution Approach 2:
The patent introduces a new dimensional representation by organizing perception data into layered costmaps with multiple abstraction levels rather than transmitting flat lists of objects. This dimensional reorganization allows the system to convey accurate environmental information through a more compact structured format, reducing the quantity of signaling required while preserving perception accuracy.
3Loss of energy
If layered costmaps and incremental CPM transmission are implemented, then the network resource usage is reduced, but the device complexity increases
Solution Approach 1:
The patent implements multi-functional costmap structures that serve multiple purposes: they represent environmental data, enable selective data transmission, and provide a framework for incremental updates. This universal costmap approach consolidates multiple functions into a single data structure, reducing the need for separate processing systems and thereby mitigating the increase in device complexity while achieving network resource efficiency.
Solution Approach 2:
The patent performs preliminary processing by pre-computing and structuring perception data into layered costmaps before transmission. This preliminary action organizes the data in advance, enabling more efficient incremental updates and selective sharing without requiring complex real-time processing during communication, thus reducing the perceived device complexity during operation.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Disclosed embodiments are related to techniques for implementing Collective Perception Services in Intelligent Transport Systems. Embodiments include technologies for sharing layered costmaps and/or sharing perceived object clusters in Collective Perception Messages. Other embodiments may be described and/or claimed.