ADS Algorithm Scheduling by Partitioned Time-Window Execution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated Driving Systems face computational budget constraints due to limited resources, leading to potential delays and inefficiencies in decision-making, which restrict the deployment of advanced algorithms and functionalities.
Innovation Solution
A method and system that split computational tasks into multiple time-windows, allowing algorithms to be executed at lower frequencies when necessary, thereby adhering to the available computational budget while ensuring real-time performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If advanced algorithms with higher computational requirements are deployed in ADS, then functionality and safety are improved, but computational budget constraints are exceeded
Solution Approach 1:
The patent segments algorithms into different execution frequencies (first frequency for critical functions, second frequency for non-critical functions). This segmentation allows the system to allocate computational resources differently based on algorithm importance, enabling advanced safety-critical algorithms to run at full frequency while less critical algorithms run at reduced frequency, thus fitting within computational budget constraints.
2Speed
If algorithms are executed at higher frequency, then real-time performance is improved, but computational resources are consumed faster
Solution Approach 1:
The patent implements dynamic execution frequency adjustment based on algorithm criticality. Critical algorithms maintain high execution frequency for real-time performance, while non-critical algorithms dynamically reduce to lower frequencies during computational budget constraints. This dynamic approach optimizes the balance between real-time performance and resource consumption.
3Productivity
If computational tasks are consolidated into single time-windows, then processing efficiency is improved, but algorithm complexity increases when partitioning is required
Solution Approach 1:
The patent performs preliminary classification of algorithms into critical and non-critical categories before execution. This preliminary action enables the system to pre-determine which algorithms require high-frequency execution and which can tolerate lower frequencies, simplifying the partitioning logic and reducing runtime complexity while maintaining processing efficiency.
Data Source
Figure 1
Figure 2a~2b
Figure 3
AI summary
Methods for executing computational work of an Automated Driving System, ADS, of a vehicle and related aspects are disclosed. The ADS is configured to execute ADS-function algorithms at a set frequency defining a scheduling time-window for execution of one or more algorithms, and the method comprises in response to an ADS-function algorithm having a computational runtime exceeding an available computational budget of an upcoming scheduling time-window, and in response to the algorithm fulfilling one or more conditions for partitioned execution, splitting the ADS-function algorithm into a plurality of processing portions. The method further comprises executing the plurality of processing portions of the ADS-function algorithm sequentially over a corresponding plurality of scheduling time-windows.