Autonomous Vehicle Intersection Planning Under Occlusion Constraints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in safely navigating minor-major intersections, where they must yield to traffic on major roads with varying turn types, speed limits, and road topologies, often encountering occlusions that complicate the assessment of safe maneuvers.
Innovation Solution
The implementation of a control system within autonomous vehicles that utilizes sensors, map data, and shadow tracks to determine commit regions and generate trajectories, considering induced kinematic discomfort and post-encroachment time, while accounting for occlusions through predictive modeling and cost-based analysis to ensure safe execution of maneuvers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If autonomous vehicles use complex sensor systems and control mechanisms to navigate minor-major intersections, then safety and maneuver assessment capability improve, but device complexity increases
Solution Approach 1:
The control system segments the intersection navigation task into distinct functional modules: sensor data acquisition, occlusion detection, commit region determination, trajectory generation, and maneuver execution. Each module handles a specific aspect of the navigation challenge, making the overall complex system more manageable and maintainable while achieving high safety standards through coordinated operation of specialized subsystems
Solution Approach 2:
The system performs preliminary actions by pre-determining commit regions and generating shadow tracks before actual maneuver execution. This advance planning allows the vehicle to assess potential trajectories and identify safe commit regions in advance, improving safety through proactive risk assessment rather than reactive responses during critical maneuver phases
2Reliability
If autonomous vehicles perform detailed cost-based analysis considering induced kinematic discomfort and post-encroachment time, then maneuver safety improves, but computation time and processing complexity increase
Solution Approach 1:
The system applies partial action by focusing computational resources on the most critical factors for safety: occlusion detection, commit region boundaries, and post-encroachment time assessment. Rather than analyzing all possible trajectory variables in equal detail, the system prioritizes the subset of parameters that have the greatest impact on maneuver safety, achieving adequate safety assessment with reduced computation time
Solution Approach 2:
The system changes parameters by transforming complex continuous trajectory optimization into discrete parameter evaluation. By converting the continuous space of possible trajectories into discrete commit region boundaries and shadow track parameters, the system enables efficient computation of safety metrics like induced kinematic discomfort and post-encroachment time without requiring exhaustive simulation of all possible maneuver variations
3Measurement precision
If autonomous vehicles account for occlusions through predictive modeling, then assessment accuracy improves, but system complexity and processing requirements increase
Solution Approach 1:
The system introduces shadow tracks as intermediary representations that mediate between sensor observations and commit region determination. Shadow tracks provide a simplified predictive model of potential road user trajectories behind occlusions, enabling the system to assess safety without directly modeling the full complexity of occluded environments. This intermediary representation maintains assessment accuracy while reducing computational burden
Data Source
AI summary
Approaches to managing navigation of autonomous vehicles through minor-major intersections are disclosed. A minor-major intersection is detected. Shadow tracks are generated for occlusions associated with the minor-major intersection. A maneuver evaluation is performed based on induced kinematic discomfort and post-encroachment time. Preliminary lateral and longitudinal planning is performed based on shadow tracks, induced kinematic discomfort and post-encroachment time to generate one or more proposed trajectories. Final trajectory generation is performed by refining at least one of the one or more proposed trajectories to generate the final trajectory. The autonomous vehicle performs a selected maneuver corresponding to the final trajectory within the minor-major intersection.