Autonomous Driving Trajectory Abnormality Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving systems face challenges in maintaining safe navigation when the processor's driving trajectory generation function fails, as existing technologies lack a robust mechanism to handle abnormalities in map information processing, potentially leading to inaccurate trajectory generation and increased risk of collisions.
Innovation Solution
An autonomous driving apparatus and method that includes sensors to detect nearby vehicles, a memory for storing map information, and a processor to generate driving trajectories. The system determines if the trajectory generator is abnormal, requests new map information from nearby vehicles, verifies its reliability, and controls autonomous driving based on verified information to ensure safe navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous driving system relies on a single processor to generate driving trajectories based on map information, then the system structure remains simple, but the reliability of autonomous driving deteriorates when the processor function becomes abnormal
Solution Approach 1:
The patent applies local quality by implementing abnormality detection specifically for the driving trajectory generation function rather than monitoring the entire system. The control processor selectively monitors trajectory data values to detect abnormalities, focusing computational resources on the critical function of trajectory generation while maintaining overall system simplicity.
Solution Approach 2:
The patent implements preliminary action by detecting abnormalities in the driving trajectory generation function before they lead to unsafe driving conditions. The control processor continuously monitors trajectory data values and identifies deviations from expected ranges in advance, allowing the system to request updated map information proactively rather than reactively after a failure occurs.
2Reliability
If the system requests new map information from nearby vehicles when abnormality is detected, then the reliability of driving trajectory generation is improved, but the complexity of information verification and communication increases
Solution Approach 1:
The patent applies feedback by establishing a closed-loop system where the control processor monitors driving trajectory data, detects abnormalities, requests updated map information from nearby vehicles, verifies the received information, and updates the map data. This feedback mechanism ensures continuous improvement of map information reliability while maintaining automated verification processes to manage complexity.
Solution Approach 2:
The patent uses nearby vehicles as intermediaries to transfer updated map information to the autonomous vehicle. Instead of directly accessing complex map databases or requiring manual intervention, the system leverages nearby vehicles as mediators that already possess current map information, simplifying the information acquisition process while enhancing reliability.
3Reliability
If the system continuously monitors driving trajectory data to detect abnormalities, then the safety of autonomous driving is improved, but the computational load and processing time increase
Solution Approach 1:
The patent applies partial action by monitoring only the critical driving trajectory data values generated by the processor rather than analyzing all sensor data and system parameters. The control processor focuses computational resources on detecting abnormalities in trajectory data values, which are the most indicative of processor function failures, thereby reducing overall computational load and energy consumption while maintaining high detection accuracy.
Data Source
AI summary
Disclosed are an autonomous driving apparatus and method for an ego vehicle that autonomously travels. The autonomous driving apparatus includes a first sensor to detect a nearby vehicle nearby an ego vehicle, a memory to store map information, and a processor including a driving trajectory generator to generate a first driving trajectory of the ego vehicle and a second driving trajectory of the nearby vehicle based on the map information stored in the memory and a control processor configured to control autonomous driving of the ego vehicle based on the first and second driving trajectories generated by the driving trajectory generator.