Autonomous Vehicle Passenger Safety via Occupancy-Aware Collision Simulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional Autonomous Vehicles (AVs) lack the capability to effectively mitigate collisions with unpredictable external factors, as they are primarily focused on avoiding collisions rather than mitigating injury to passengers in unavoidable accidents.
Innovation Solution
Integration of interior and exterior sensor data to determine passenger occupancy and simulate collision scenarios, allowing the AV to rank driving actions that minimize injury severity metrics such as Principal Direction of Force (PDOF), Vehicle change in velocity (Delta-V), and Occupant Impact Velocity (OIV), enabling the selection of actions that reduce harm to passengers during unavoidable collisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the AV focuses on avoiding collisions through exterior sensor systems, then collision avoidance capability is improved, but the ability to mitigate injury in unavoidable collisions deteriorates
Solution Approach 1:
The system performs preliminary actions by detecting passenger occupancy positions before a collision occurs and pre-calculating multiple potential driving actions with their corresponding injury severity metrics. This allows the AV to have mitigation strategies ready in advance, selecting the action that minimizes passenger injury even when collision avoidance is not possible.
Solution Approach 2:
The system uses simulation to create virtual copies of collision scenarios and calculates injury severity metrics for each potential driving action without actually executing them. This allows the AV to evaluate multiple hypothetical outcomes and select the optimal mitigation strategy based on simulated results before the real collision occurs.
2Object-affected harmful factors
If the AV integrates interior and exterior sensor systems to determine passenger occupancy and simulate collision scenarios, then passenger safety is improved, but device complexity increases
Solution Approach 1:
The computing system performs multiple functions using the same integrated sensor data: it detects passenger occupancy, determines their positions, simulates collision scenarios, calculates injury severity metrics, and selects optimal driving actions. This multi-functionality approach consolidates what could be separate complex systems into a unified processing framework.
Solution Approach 2:
The system replaces complex mechanical safety systems with computational simulations and data processing. Instead of physical mechanisms for assessing collision risks, the system uses sensor data integration, virtual scenario simulation, and algorithmic calculation of injury metrics to determine safety-optimal actions.
3Object-affected harmful factors
If the AV calculates multiple sets of driving actions and ranks them based on injury severity metrics, then passenger protection is improved, but processing time increases
Solution Approach 1:
The system calculates multiple sets of driving actions (excessive action) and ranks them by injury severity, but in practice, once the optimal mitigation action is identified through this comprehensive evaluation, the system executes only that single best action rather than considering all possibilities during actual collision response.
Solution Approach 2:
The system performs the computationally intensive task of calculating and ranking multiple driving actions in advance, before a collision becomes imminent. This preliminary evaluation allows the AV to have pre-assessed options ready, reducing the real-time decision burden when actual collision avoidance or mitigation is required.
Data Source
AI summary
Systems and methods can improve passenger safety for an Autonomous Vehicle (AV) based on the integration of sensor data captured by the AV's interior and exterior sensors. The AV can determine passenger occupancy data corresponding to where each passenger is detected within the AV by the interior sensors. The AV can determine multiple sets of one or more driving actions that the AV can perform at a future time. The AV can generate crash impact data corresponding to where each passenger is detected from one or more simulated collisions between the AV and one or more objected detected by the exterior sensors when the AV performs one or more sets of driving actions from among the multiple sets. The AV can determine ranked sets of driving actions based on the passenger occupancy data and the crash impact data.