Vehicle Control Device Risk Estimation Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle control systems do not effectively reduce the process load associated with short-term risk estimation and do not consider the reduction of process load in calculating potential risks near a vehicle.
Innovation Solution
A vehicle control device and method that includes a peripheral situation recognition unit, a potential risk estimation unit, and a driving control unit to estimate and manage potential risks by recognizing obstacles and controlling vehicle steering and acceleration based on estimated risks, with an optional traffic scenario storage unit to store and search for estimation results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the system estimates both short-term risk and long-term risk of contact between obstacle and own vehicle, then the reliability of risk assessment is improved, but the device complexity and calculation amount increase
Solution Approach 1:
The risk estimation function is segmented into two distinct units: a short-term risk estimation unit that processes immediate contact risks using simplified calculations, and a long-term risk estimation unit that handles potential future risks using pre-stored traffic scenario data. This segmentation allows each unit to operate with appropriate complexity levels, maintaining overall reliability while reducing total calculation burden.
Solution Approach 2:
Traffic scenario data including long-term risk information is pre-calculated and stored in a traffic scenario storage unit during off-line phases. During on-line operation, the system only needs to retrieve and compare this pre-stored data with current sensor inputs, eliminating the need for real-time long-term risk calculations and significantly reducing computational complexity during critical driving moments.
2Productivity
If the system focuses only on short-term risk estimation to reduce calculation amount, then the productivity is improved, but the reliability of potential risk detection deteriorates
Solution Approach 1:
The system performs preliminary action by pre-storing traffic scenario data that includes long-term risk information during off-line phases. This allows the on-line system to quickly retrieve and compare pre-computed risk data with current sensor inputs, maintaining high processing speed while ensuring comprehensive risk detection coverage without real-time calculation burdens.
Solution Approach 2:
The traffic scenario storage unit acts as an intermediary between sensor inputs and risk assessment outputs. It stores pre-computed traffic scenario data that mediates between raw sensor data and final risk decisions, enabling the system to quickly query potential risks without performing complex real-time calculations, thus maintaining both speed and reliability.
3Adaptability or versatility
If the system stores and searches traffic scenario data by keywords, then the adaptability to different risk situations is improved, but the device complexity increases
Solution Approach 1:
The system creates simplified keyword representations of complex traffic scenarios and stores these keywords along with associated risk data. During operation, the system copies and matches keywords from current sensor inputs against the stored keyword database, enabling flexible adaptation to different risk situations through simple string matching rather than complex pattern recognition, thus improving adaptability while controlling complexity.
Data Source
AI summary
A vehicle control device includes: a peripheral situation recognition unit (132) configured to recognize a peripheral situation of an automatic driving vehicle; a driving control unit (140, 160, (138)) configured to control one or both of steering and an acceleration or deceleration speed of the vehicle based on the peripheral situation recognized by the peripheral situation recognition unit; and a potential risk estimation unit (138) configured to estimate presence or absence and classification of a potential risk meeting with an obstacle based on classification of a target recognized by the peripheral situation recognition unit and a positional relation between the vehicle and the target. The driving control unit performs the driving control based on an estimation result of the potential risk estimation unit.