自动驾驶汽车撞车事故因果分析的句子重新采样的BERT-CRF模型,来自大规模事故叙述文本数据
Ruixu Pan1, Quan Yuan1, Jiaming Cao2
1School of Transportation, Tongii University, 201804 Shanghai, China; The Key Laboratory of Road and Traffic Engineering Ministry of Education at Tongji University, 201804 Shanghai, China.
Accident; analysis and prevention
|August 8, 2025
概括
本研究引入了一种新的模型,用于从文本叙述中分析自动驾驶汽车 (AV) 撞车原因,识别后端和车道交换碰撞是由于人机交互和感知问题的高风险场景.
科学领域:
- 交通安全 交通安全 交通安全
- 人工智能的人工智能
- 自然语言处理自然语言处理.
背景情况:
- 自动驾驶汽车 (AV) 的安全至关重要,但事故因果分析往往忽略了非结构化的叙述数据.
- 现有的方法与数据不平衡和崩叙述固有的小样本大小扎.
研究的目的:
- 开发一种新的框架来分析使用非结构化撞击叙述的AV撞击因果关系.
- 识别高风险撞车场景及其潜在的因果因素.
主要方法:
- 开发了一个 Sentence-resampled BERT-CRF模型,从叙事中提取因果运动链 (CMC).
- 为了系统分析,采用了以DREAM为灵感的层次性因果归因框架.
- 通过句子级重新抽样来解决数据不平衡.
主要成果:
- 该模型在完整数据上达到98.03%的准确性,在10%的数据上达到96.14%的准确性.
- 后端 (48.57%) 和变车道 (17.04%) 的碰撞被确定为高风险场景.
- 原因因素包括常规车辆 (CV) 接近,AV决策和意图识别延迟.
结论:
- 拟议的框架有效地弥合了非结构化数据和AV安全的因果推理.
- 关键的因果因素包括人机交互,环境感知和道路基础设施.
- 这些发现有助于AV制造商优化算法和当局制定法规.
相关概念视频
Elastic Collisions: Case Study
14.3K
Elastic collision of a system demands conservation of both momentum and kinetic energy. To solve problems involving one-dimensional elastic collisions between two objects, the equations for conservation of momentum and conservation of internal kinetic energy can be used. For the two objects, the sum of momentum before the collision equals the total momentum after the collision. An elastic collision conserves internal kinetic energy, and so the sum of kinetic energies before the collision equals...
14.3K
Types of Collisions - II
8.1K
When two or more objects collide with each other, they can stick together to form one single composite object (after collision). The total mass of the object after the collision is the sum of the masses of the original objects, and it moves with a velocity dictated by the conservation of momentum. Although the system's total momentum remains constant, the kinetic energy decreases, and thus such a collision is an inelastic collision. Most of the collisions between objects in daily life are...
8.1K
Collisions in Multiple Dimensions: Problem Solving
4.4K
In multiple dimensions, the conservation of momentum applies in each direction independently. Hence, to solve collisions in multiple dimensions, we should write down the momentum conservation in each direction separately. To help understand collisions in multiple dimensions, consider an example.
A small car of mass 1,200 kg traveling east at 60 km/h collides at an intersection with a truck of mass 3,000 kg traveling due north at 40 km/h. The two vehicles are locked together. What is the...
A small car of mass 1,200 kg traveling east at 60 km/h collides at an intersection with a truck of mass 3,000 kg traveling due north at 40 km/h. The two vehicles are locked together. What is the...
4.4K
Collisions in Multiple Dimensions: Introduction
5.6K
It is far more common for collisions to occur in two dimensions; that is, the initial velocity vectors are neither parallel nor antiparallel to each other. Let's see what complications arise from this. The first idea is that momentum is a vector. Like all vectors, it can be expressed as a sum of perpendicular components (usually, though not always, an x-component and a y-component, and a z-component if necessary). Thus, when the statement of conservation of momentum is written for a...
5.6K
Types Of Collisions - I
7.5K
When two objects come in direct contact with each other, it is called a collision. During a collision, two or more objects exert forces on each other in a relatively short amount of time. A collision can be categorized as either an elastic or inelastic collision. If two or more objects approach each other, collide and then bounce off, moving away from each other with the same relative speed at which they approached each other, the total kinetic energy of the system is said to be conserved. This...
7.5K
Regression Analysis
6.0K
Regression analysis is a statistical tool that describes a mathematical relationship between a dependent variable and one or more independent variables.
In regression analysis, a regression equation is determined based on the line of best fit– a line that best fits the data points plotted in a graph. This line is also called the regression line. The algebraic equation for the regression line is called the regression equation. It is represented as:
In regression analysis, a regression equation is determined based on the line of best fit– a line that best fits the data points plotted in a graph. This line is also called the regression line. The algebraic equation for the regression line is called the regression equation. It is represented as:
6.0K


