Semi-Automated Driving Using Pre-Recorded Route Waypoints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous driving technologies require full vehicle autonomy for navigating daily commutes, which is resource-intensive and unnecessary for simple routes, leading to a need for a more efficient method to record and repeat daily driving routes.
Innovation Solution
A vehicle can record a driving route as waypoints within a simple two-dimensional feature map, using sensors to identify landmarks and navigate autonomously, allowing for partial autonomy and conserving computer memory by avoiding complex algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If full autonomous driving technology is deployed for daily commutes, then navigation capability is improved, but computational resource consumption and system complexity increase unnecessarily
Solution Approach 1:
The patent segments the autonomous driving system into two distinct operational modes: a simplified pre-recorded route following mode for daily commutes, and a full autonomous driving mode for complex situations. This segmentation allows the system to use only the necessary level of complexity for each task, avoiding unnecessary computational overhead for routine navigation while maintaining full capability when needed.
Solution Approach 2:
The patent implements partial automation by using pre-recorded routes that capture only the essential navigation information for repetitive daily commutes. This partial action approach provides sufficient automation for simple routes without deploying the complete, resource-intensive full autonomous driving system, thereby reducing computational resource consumption while maintaining adequate navigation capability.
2Measurement precision
If full autonomous driving algorithms are used, then navigation accuracy is improved, but computer memory consumption increases
Solution Approach 1:
The patent extracts and stores only the essential route information (waypoints, landmarks, and path geometry) into a simplified feature map for pre-recorded routes. This extraction process removes unnecessary computational elements from the full autonomous driving algorithms, retaining only the critical data needed for accurate route following while significantly reducing memory consumption.
Solution Approach 2:
The patent creates simplified copies of route information by recording waypoints and landmarks into a compact feature map representation. This copying approach stores only the necessary navigational data in a reduced format, maintaining route following accuracy while using minimal computer memory compared to storing complete environmental models or complex algorithmic structures.
3Quantity of substance
If simple two-dimensional feature maps are used, then memory usage is reduced, but navigation reliability may be compromised
Solution Approach 1:
The patent performs preliminary recording of routes during a first pass, capturing waypoints, landmarks, and path geometry into the feature map before actual navigation occurs. This preliminary action ensures that all necessary navigational information is pre-processed and stored in the simplified structure, enabling reliable route following during subsequent traversals without requiring complex real-time processing or large memory allocations.
Solution Approach 2:
The patent implements a driver feedback mechanism where the driver can confirm or correct the recorded route during the initial recording phase. This feedback loop ensures that the simplified feature map accurately represents the intended path and accounts for real-world conditions, thereby maintaining navigation reliability despite using a memory-efficient two-dimensional representation instead of more complex environmental models.
Data Source
AI summary
A system for use in a vehicle, the system comprising one or more sensors, one or more processors coupled to the one or more sensors, and a memory including instructions that cause the one or more processors to perform a method. The method comprises retrieving a stored route for the vehicle that comprises a plurality of waypoints corresponding to different locations along the route, each waypoint associated with features along the route on a feature map, and navigating the vehicle along the stored route by navigating the vehicle from waypoint to waypoint in the stored route using the one or more sensors to: detect one or more features in an area surrounding the vehicle; and localize the vehicle at each waypoint by comparing the one or more features in the area surrounding the vehicle with the one or more features associated with each respective waypoint in the feature map.