Autonomous Vehicle Stop Request Replanning for Safe Target Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in efficiently responding to requests for immediate or speed-reducing maneuvers, particularly in identifying suitable target locations and adapting trajectory plans when initial locations become unavailable.
Innovation Solution
The system enables autonomous vehicles to analyze various data sources, including map and sensor data, to identify and adapt to target locations for speed-reducing maneuvers, such as stopping, by evaluating factors like urgency, quality, and availability, and continuously updating the trajectory plan based on real-time data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If the AV system immediately executes a stop request upon receiving it, then the response time is reduced, but the safety and appropriateness of the maneuver may be compromised due to insufficient evaluation of target location quality and trajectory feasibility
Solution Approach 1:
The system performs preliminary evaluation of target locations and trajectory plans before executing the stop maneuver. Multiple candidate locations are pre-assessed for quality metrics (safety, accessibility, suitability) and trajectory feasibility is pre-checked, allowing the system to quickly select from pre-evaluated options rather than evaluating from scratch during emergency stopping
Solution Approach 2:
The system dynamically adjusts the decision-making process based on the urgency of the stop request. For high-urgency requests, the system uses pre-computed safety margins and predefined acceptable target location criteria to accelerate decision-making, while maintaining the core evaluation framework. The trajectory planner dynamically replans if obstacles are detected, balancing speed and safety adaptively
2Reliability
If the AV system conducts comprehensive evaluation of multiple target locations and trajectory plans, then the quality and safety of the maneuver is improved, but the processing time and computational complexity increase
Solution Approach 1:
The evaluation process is segmented into hierarchical levels: (1) rapid filtering of obviously unsuitable target locations based on basic criteria, (2) detailed quality assessment of remaining candidates using multiple metrics, and (3) trajectory feasibility analysis. This segmentation allows the system to quickly eliminate poor options and focus computational resources on evaluating promising candidates in detail
Solution Approach 2:
The system changes evaluation parameters dynamically based on context. For normal stopping requests, comprehensive quality metrics are used. For urgent stop requests, the system adjusts parameters to prioritize locations meeting minimum safety thresholds while reducing the depth of evaluation for less critical factors, enabling faster decision-making without completely sacrificing quality
3Device complexity
If the AV system maintains a fixed trajectory plan from current location to target location, then the planning complexity is reduced, but the system cannot adapt when the target location becomes unavailable or inappropriate during execution
Solution Approach 1:
The system continuously monitors the execution status of the trajectory plan and compares actual vehicle position and environmental conditions against the planned path. When deviations or obstacles are detected, feedback triggers automatic replanning to generate new trajectories to the same or alternative target locations, ensuring adaptability while maintaining structured planning through iterative refinement
Solution Approach 2:
The trajectory planning system is designed to serve multiple functions: initial path generation, real-time obstacle avoidance, and adaptive replanning. The same planning framework handles both predetermined routes and dynamic route adjustments, reducing overall system complexity by using a unified planning architecture rather than separate specialized systems
4Measurement precision
If the AV system evaluates multiple factors including map data, sensor data, traffic conditions, and quality metrics, then the accuracy of target location selection is improved, but the data processing complexity and computational load increase
Solution Approach 1:
Data processing is segmented into modular components: map data processing, sensor data processing, traffic condition analysis, and quality metric computation. Each module handles specific data types independently and outputs standardized results that are integrated by the target location selection algorithm, reducing overall complexity through functional decomposition
Solution Approach 2:
Multiple data sources (map data, sensor data, traffic conditions) and evaluation criteria (safety, accessibility, suitability metrics) are merged into a unified quality assessment framework. The system integrates diverse inputs using weighted scoring and constraint satisfaction methods, combining complex information streams into a single target location selection decision that considers all factors simultaneously
Data Source
AI summary
Among other things, a vehicle drives autonomously on a trajectory through a road network to a goal location based on an automatic process for planning the trajectory without human intervention; and an automatic process alters the planning of the trajectory to reach a target location based on a request received from an occupant of the vehicle to engage in a speed-reducing maneuver.