Основные понятия
Analyzing the safety of driverless automated driving systems compared to human-operated vehicles in San Francisco.
Аннотация
The content delves into the safety aspects of driverless automated driving systems (ADS) compared to human-driven vehicles. It analyzes crash rates, characteristics, and data from various sources such as CPUC, DMV, and NHTSA. The study focuses on supervised AVs, driverless AV pilots, and deployments by companies like Waymo and Cruise in San Francisco. Key highlights include comparisons of crashes per million miles (CPMM), injury rates, collision types, external factors affecting crashes, and involvement of vulnerable road users. The analysis reveals that supervised AVs have similar CPMM to Uber drivers while Waymo shows lower CPMM but Cruise exhibits higher CPMM than human drivers. Limitations are acknowledged due to data redactions and sample sizes.
Structure:
- Introduction to ADS Safety Concerns
- Regulatory Framework for AVs in California
- Data Extraction Methods for Analysis
- Comparison of Crash Rates: Supervised vs Human-Operated Vehicles
- Insights from Literature Review on AV Crashes
- Comparison of Crash Characteristics among TNCs and AVs
- Conclusions & Future Studies with Limitations Acknowledged
Статистика
The study finds that supervised AV has almost equivalent crashes per million miles (CPMM) as Uber human driving.
Driverless Waymo AV has a lower CPMM than Uber human driving.
Driverless Cruise AV has a higher CPMM than Uber human driving.
Цитаты
"Lower frequency of injury crashes offers encouragement about the potential for safety improvement."
"The trend is upwards but only very slightly in terms of crash-per-mile statistic."
"Driverless operations had 0 injuries (100% reduction as compared to human driving)."