Keyframe-Based Autonomous Vehicle Operation for Occlusion Handling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in handling unexpected situations, such as occlusions, where objects or pedestrians may be hidden, leading to unpredictable scenarios that existing systems struggle to manage effectively.
Innovation Solution
A keyframe-based system that uses sensors, feature extractors, and reasoning logic to select appropriate driving parameters by analyzing occlusion objects, lane structures, and vehicle states, generating maximum and minimum suggested limits for autonomous vehicle operation, allowing the vehicle to adapt and navigate safely through complex environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional autonomous driving systems use predictable trajectory planning, then normal driving operation is efficient, but unexpected situations such as occlusions cannot be handled effectively
Solution Approach 1:
The system performs preliminary action by proactively detecting occlusion objects and predicting potential hazards before they materialize into actual threats. The reasoning logic identifies occlusion scenarios in advance and pre-computes safe trajectory adjustments, allowing the vehicle to react before collisions or unfavorable situations occur.
Solution Approach 2:
The system applies beforehand cushioning by generating maximum and minimum suggested limits for driving parameters that create a safety buffer around the vehicle's path. These limits act as protective constraints that cushion the vehicle from potential hazards hidden by occlusions, preventing dangerous situations before they can occur.
2Reliability
If the system generates maximum and minimum suggested limits for driving parameters, then safety is improved, but computational complexity increases
Solution Approach 1:
The system segments the complex control problem into distinct components: occlusion detection, keyframe model selection, and parameter limit generation. By dividing the reasoning logic into modular functional blocks that process different aspects independently, the system manages computational complexity while maintaining comprehensive safety checks.
Solution Approach 2:
The system introduces an intermediary layer (the reasoning logic) that sits between sensor input and ECU control commands. This intermediary processes environmental state information and vehicle state information to generate suggested parameter limits, mediating between raw data and control actions to simplify the overall system architecture.
3Reliability
If the system proactively reacts to occlusions by adjusting driving parameters, then accident risk is reduced, but normal driving efficiency may decrease
Solution Approach 1:
The system applies partial action by adjusting driving parameters only to the extent necessary to maintain safety within suggested limits, rather than overly constraining all movements. The ECU commands the vehicle to operate within maximum and minimum limits that allow normal driving efficiency while providing sufficient buffer to prevent accidents.
Solution Approach 2:
The system dynamically adjusts driving parameters based on real-time environmental conditions and occlusion detection. When occlusions are detected, the reasoning logic generates appropriate parameter limits that temporarily modify driving behavior; when no occlusions are present, normal efficient driving resumes, making the system adaptive rather than statically restrictive.
Data Source
AI summary
According to one aspect, keyframe based autonomous vehicle operation may include collecting vehicle state information and collecting environment state information. A size of an object within the environment, a distance between the object and the autonomous vehicle, and a lane structure of the environment through which the autonomous vehicle is travelling may be determined. A matching keyframe model may be selected based on the size of the object, the distance from the object to the autonomous vehicle, the lane structure of the environment, and the vehicle state information. Suggested limits for a driving parameter associated with autonomous vehicle operation may be generated based on the selected keyframe model. The autonomous vehicle may be commanded to operate autonomously according to the suggested limits for the driving parameter.