Autonomous Vehicle Collision Cost Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous driving vehicles face challenges in minimizing damage during unavoidable collisions, as conventional methods do not effectively assess and mitigate potential damage from collisions with various objects in the driving environment.
Innovation Solution
The vehicle employs a collision cost calculation system that analyzes the relative positions and speeds of surrounding objects, using cost functions and algorithms to determine the path that minimizes damage by selecting the object with the lowest collision cost, thereby planning a trajectory to collide with that object.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If the vehicle slows or stops as soon as possible while maintaining the same heading direction, then the vehicle can quickly respond to potential collisions, but this approach may not minimize the damage caused by unavoidable collisions
Solution Approach 1:
The system performs preliminary analysis of the driving environment and potential collision scenarios before the collision occurs. By examining surrounding objects, calculating collision costs, and determining optimal paths in advance, the system prepares multiple trajectory options that would minimize damage if a collision becomes unavoidable, rather than simply braking or maintaining heading
Solution Approach 2:
The system dynamically adjusts the vehicle's trajectory by calculating multiple possible paths and selecting the one with the least collision cost. Instead of following a fixed response pattern (brake or maintain heading), the system continuously evaluates changing environmental conditions and computes optimal dynamic paths that adapt to the specific spatial and temporal context of potential collisions
2Object-affected harmful factors
If the vehicle calculates multiple paths and selects the one with least collision cost, then the potential damage from unavoidable collision is greatly reduced, but this requires complex analysis and calculation of collision costs
Solution Approach 1:
The system uses the vehicle's existing sensors and onboard computing resources to perform collision cost calculations, rather than requiring external infrastructure or specialized dedicated hardware. The existing autonomous driving perception and planning systems are extended to include collision cost analysis, allowing the vehicle to serve its own safety optimization needs using its current capabilities
3Object-affected harmful factors
If the vehicle examines and analyzes the surrounding driving environment at the point in time, then the optimal path to reduce damage can be determined, but this requires real-time processing of environmental data
Solution Approach 1:
The system continuously performs preliminary environmental analysis and maintains updated information about surrounding objects, their positions, and potential collision risks even during normal operation. This ongoing preliminary examination ensures that when a collision becomes unavoidable, the analysis is already partially complete or can be quickly finalized, reducing the time needed for optimal path determination at the critical moment
Data Source
AI summary
It is determined an ADV is inevitable to collide with at least one of the objects surrounding the ADV based on the relative positions and speeds between the ADV and the objects in view of the physical dimensions of the ADV. An object may be another vehicle, a pedestrian, a bicycle, a static obstacle. For each of the objects, a collision cost between the ADV and the object is calculated using a set of one or more cost functions or cost algorithms. A collision cost represents an amount of potential damage if the collision is to occur. One of the objects is selected whose collision cost is the least amongst the objects. A path or trajectory is planned for the ADV leading or towards to the selected object to minimize the potential damage when the ADV potentially collide with the selected object compared to the remaining objects.