Dual-Channel ADAS Trajectory Evaluation for Common-Cause Error Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing advanced driver assistance systems (ADAS) face challenges in ensuring the safety and reliability of automated driving functions, particularly at SAE Levels 3 and above, where the driver is not continuously monitoring the system, while minimizing functional availability reductions.
Innovation Solution
A system with two independent subsystems (PAC and SAC) generate and assess vehicle trajectories using separate environmental models, applying a unified safety metric to evaluate and select the safest path, ensuring redundancy and diversity to prevent common-cause errors, and a third subsystem selects the final trajectory based on consensus safety scores.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple independent subsystems are used to generate and assess trajectories, then reliability is improved, but device complexity increases
Solution Approach 1:
The system is divided into multiple independent subsystems (PAC and SAC channels), each capable of independently generating environmental models and planning trajectories. This segmentation allows parallel processing of safety-critical functions while maintaining system reliability through redundancy.
Solution Approach 2:
The patent implements redundant copies of critical subsystems (environmental model generation, trajectory planning, safety assessment) in independent channels. Each channel produces identical functional outputs through separate computational paths, ensuring that if one channel fails, the other can take over without compromising safety.
2Reliability
If redundant subsystems are implemented, then reliability is improved, but computational resources are consumed
Solution Approach 1:
The system performs preliminary safety assessments by evaluating multiple candidate trajectories against safety metrics before final selection. This advance evaluation prevents the need for complex real-time computations during critical moments, reducing peak computational energy consumption while maintaining high reliability.
Solution Approach 2:
The patent dynamically adjusts computational parameters such as the number of candidate trajectories generated, assessment depth, and planning horizon based on operational context. This allows the system to optimize the balance between computational resource usage and safety assurance, consuming more resources when needed and less when conditions permit.
3Reliability
If safety assessment is performed on multiple trajectories, then reliability is improved, but processing time increases
Solution Approach 1:
The system performs partial safety assessments on multiple trajectories simultaneously, evaluating critical safety parameters for all candidates before conducting detailed assessments on the most promising options. This approach ensures adequate safety validation without the time cost of exhaustive assessment of every possible trajectory.
Solution Approach 2:
The system pre-evaluates trajectories against safety metrics and constraints before final selection, filtering out unsafe options early in the process. This preliminary screening reduces the number of trajectories requiring detailed assessment, thereby maintaining high safety validation standards while minimizing processing time.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The invention relates to a system (1) for operating a driver assistance system of a vehicle (3), the system (1) comprising: a first sub-system (PAC), which is designed to produce a first environment model and to plan one or more first trajectories for the vehicle (3) in accordance with the first environment model; and a second sub-system (SAC), which is designed to produce a second environment model and to plan one or more second trajectories for the vehicle (3) in accordance with the second environment model. The first sub-system (PAC) and the second sub-system (SAC) are each designed to carry out a safety evaluation of both the one or more first trajectories and the one or more second trajectories on the basis of a metric.