Autonomous Vehicle Obstacle Decisions With Confidence-Based Delay
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving vehicles face challenges in determining the appropriate response to obstacles due to uncertainty in obstacle movement and sensing reliability, leading to potential safety issues and unnecessary delays or disturbances in driving experience.
Innovation Solution
The autonomous vehicle calculates a confidence score for sensed obstacles based on sensor data and determines whether to react by adjusting its path, slowing down, or stopping by considering both the confidence threshold and the distance to the obstacle, thereby delaying reactions when confidence is low and proximity is close, ensuring safety while minimizing disruptions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the ADV reacts immediately to sensed obstacles, then safety is improved, but unnecessary delays and disturbances in driving experience occur when confidence is low
Solution Approach 1:
The system changes the parameter of reaction timing based on the confidence score parameter. When confidence is high, immediate reaction occurs; when confidence is low, reaction is delayed. This dynamic parameter adjustment resolves the contradiction by adapting the response time to the reliability of the obstacle detection.
Solution Approach 2:
The system makes the reaction behavior dynamic by continuously monitoring confidence scores and adjusting whether to react immediately or delay based on current uncertainty levels. This dynamic adaptation allows the system to balance safety and driving experience smoothly.
2Ease of operation
If the ADV delays reaction to obstacles, then driving experience is improved, but safety risk increases when obstacle confidence is high
Solution Approach 1:
The system uses the confidence score as a controlling parameter that determines reaction timing. High confidence scores trigger immediate safety reactions, while low confidence scores allow delayed responses for smoother driving experience. This parameter-based control resolves the contradiction adaptively.
3Reliability
If the ADV reacts to all sensed obstacles, then safety is improved, but unnecessary disturbances occur due to false positives or uncertain detections
Solution Approach 1:
The confidence score acts as an intermediary that mediates between obstacle detection and reaction execution. It filters out low-confidence detections that are likely false positives while allowing high-confidence detections to trigger appropriate reactions, thus resolving the contradiction between safety and avoiding unnecessary disturbances.
Solution Approach 2:
The system changes reaction behavior based on the confidence score parameter threshold. By adjusting this parameter, the system can filter out false positives and uncertain detections, allowing safe operation while minimizing unnecessary disturbances to the driving experience.
4Productivity
If the ADV delays reaction until higher confidence is achieved, then unnecessary reactions are reduced, but response time increases when obstacles are real threats
Solution Approach 1:
The system dynamically changes response time based on the confidence score parameter. When confidence is already high, no delay is applied and immediate reaction occurs. When confidence is low, delayed reaction is applied to avoid false positives. This resolves the contradiction by making response time adaptive rather than fixed.
Data Source
AI summary
In one embodiment, a process is performed during controlling Autonomous Driving Vehicle (ADV). A confidence level associated with a sensed obstacle is determined. If the confidence level is below a confidence threshold, and a distance between the ADV and a potential point of contact with the sensed obstacle is below a distance threshold, then performance of a driving decision is delayed. Otherwise, the driving decision is performed to reduce risk of contact with the sensed obstacle.