Autonomous Vehicle Passing Control Using Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving systems face challenges in determining whether a stopped vehicle ahead is due to traffic flow, parked, or temporarily stopped by a driver, leading to inefficient waiting and potential hazards.
Innovation Solution
An apparatus and method using a processor to analyze sensor data, including camera and radar information, to distinguish between stopped vehicles due to traffic flow, parked vehicles, or those temporarily stopped by a driver, enabling informed passing control decisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous driving system continuously waits for a stopped target vehicle, then safety is maintained by avoiding collisions, but productivity deteriorates due to endless waiting when the vehicle is parked
Solution Approach 1:
The system performs preliminary analysis of the stopped vehicle's state (door status, occupant detection, brake lamp status) before deciding whether to wait or pass. This preliminary action allows the system to distinguish between vehicles that will soon move (traffic flow) and those that are parked, enabling informed decisions that balance safety with traffic flow efficiency
Solution Approach 2:
The system continuously monitors multiple parameters (door open/closed status, occupant presence, brake lamp status) and uses this feedback to dynamically adjust its behavior. When sensors indicate the vehicle is parked (doors closed, no occupants, brake lamps off), the system feedback triggers a passing maneuver instead of continued waiting
2Measurement precision
If the autonomous driving system performs detailed analysis to distinguish stopped vehicle types, then accuracy of passing control improves, but device complexity increases due to multiple sensors and processing requirements
Solution Approach 1:
The system uses a multi-functional sensor suite where each sensor serves multiple purposes: cameras detect door status, occupant presence, and brake lamp status; radar detects vehicle position and movement; this universal approach allows single sensors to contribute to multiple aspects of vehicle status recognition, improving accuracy without proportionally increasing complexity
Solution Approach 2:
The system merges data from multiple sensors (camera, radar, occupant detection systems) into a unified analysis framework. By combining these sensor inputs and processing them together through integrated algorithms, the system achieves high measurement precision while managing complexity through consolidated processing rather than separate independent systems
3Productivity
If the autonomous driving system immediately passes a stopped vehicle, then productivity improves by maintaining traffic flow, but safety deteriorates due to potential hazards from temporarily stopped vehicles
Solution Approach 1:
Before executing a passing maneuver, the system performs preliminary verification by checking multiple safety indicators: door status (open/closed), occupant detection (present/absent), and brake lamp status. This preliminary action ensures that vehicles temporarily stopped due to traffic flow or accidents are not mistakenly identified as parked vehicles, preventing unsafe passing while maintaining efficiency for truly parked vehicles
Data Source
AI summary
An apparatus for controlling autonomous driving of a vehicle includes a processor to control autonomous driving, and a storage to store data and an algorithm to control the autonomous driving. The processor determines whether a target vehicle in front of a host vehicle in a travelling lane of the host vehicle is stopped, and performs a passing control when the target vehicle is stopped.