Dual-Mode AV Mapping for Construction Zone Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating dynamic environments, particularly in construction areas where high-quality digital maps are inadequate, and perception systems have limited detection range, leading to difficulties in detecting and managing various boundaries, which can result in short reaction times to changes in the environment.
Innovation Solution
An autonomous vehicle control system utilizing a dual mode map that switches between dense and sparse map data, where dense map data is used in familiar areas and augmented sparse map data is generated using perception data in unfamiliar areas like construction zones to define a safe pathway.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If high quality digital maps are used to represent static objects in the environment, then the autonomous vehicle can reliably navigate known areas, but the overhead associated with verifying and distributing map data to a fleet of autonomous vehicles is substantial and changes may not be reflected timely
Solution Approach 1:
The patent segments map data into two distinct types: dense map data for stable, well-documented areas and sparse map data for dynamic or newly constructed areas. This segmentation allows the system to maintain high navigation reliability in known areas using dense maps while avoiding the substantial overhead of continuously updating dense maps in all areas. Sparse maps provide a lightweight alternative that doesn't require the same level of verification and distribution infrastructure.
Solution Approach 2:
The patent implements a dynamic map system that can switch between dense and sparse map representations based on environmental conditions and construction status. When construction activity is detected or map data becomes outdated, the system dynamically transitions to sparse map mode, allowing timely adaptation to changes without waiting for dense map updates. This dynamic approach resolves the contradiction by making the map system as flexible as the environment it navigates.
2Adaptability or versatility
If perception systems are used to sense surroundings and generate trajectories, then the autonomous vehicle can operate without high quality digital maps, but the detection range is generally limited and can be occluded by other vehicles, resulting in short reaction times
Solution Approach 1:
The patent merges perception-based navigation with map-based navigation by integrating sparse map data with real-time perception data. The sparse map provides a broader contextual framework that extends beyond the limited detection range of perception sensors, while perception data provides real-time updates on dynamic objects. This combination allows the vehicle to maintain operational flexibility in areas without high-quality maps while gaining extended awareness through map data, thereby increasing reaction time to potential hazards.
3Loss of information
If dense map data is maintained for all areas, then complete environmental information is available, but the complexity and overhead of maintaining and updating the maps becomes substantial
Solution Approach 1:
The patent applies local quality by providing different levels of map detail in different geographical areas based on their characteristics. Dense map data with complete environmental information is maintained only in stable, well-documented areas where it provides maximum value. In contrast, sparse map data with essential information only is used in dynamic areas, newly constructed areas, or regions where construction activity is detected. This local differentiation reduces map maintenance complexity while preserving environmental information completeness where it matters most.
Data Source
AI summary
An autonomous vehicle control system and method may utilize a dual mode map including sparse map data for some portions of an environment that lacks some of the data maintained in dense map data for other portions of the environment. Sparse map data may be used, for instance, to address a recently-established construction area on a roadway that is incompatible with dense map data that was previously used to operate on the roadway, enabling operation of an autonomous vehicle in the construction area to proceed even in the absence of dense map data for the construction area, e.g., by dynamically augmenting the sparse map data to incorporate additional data sensed by a perception system of the autonomous vehicle.