Autonomous vehicles are great at driving straight
Autonomous vehicles excel in straight driving, with lower accident risks than human-driven vehicles. However, a study in Nature found AVs struggle in turns and dawn/dusk conditions, emphasizing the need for improved algorithms and sensors.
Read original article
Autonomous vehicles (AVs) excel at driving straight, with Level 4 self-driving vehicles showing a significantly lower risk of accidents compared to human-driven vehicles. However, a recent study published in Nature revealed that AVs struggle more in turns and during dawn and dusk conditions. While AVs performed well in rain and fog due to radar and lidar systems, they were over five times more likely to be involved in accidents at dawn and dusk. The study emphasized the need for advanced algorithms, sensors, and infrastructure updates to support AV technology effectively. Despite the overall lower accident risk of AVs, challenges persist in specific scenarios, such as navigating turns and dealing with varying lighting conditions. More data is required to understand the precise causes of accidents involving AVs, highlighting the importance of ongoing research and development in autonomous vehicle technology.
Related
Waymo recalls entire fleet after one hits utility pole
Waymo recalls 672 self-driving vehicles due to a Phoenix incident. The recall addresses software issues related to avoiding poles. Safety improvements aim to build trust as Waymo expands services.
An Anatomy of Algorithm Aversion
The study delves into algorithm aversion, where people favor human judgment over algorithms despite their superior performance. Factors include agency desire, emotional reactions, and ignorance. Addressing these could enhance algorithm acceptance.
Waymo the Leapfrog
Waymo, a Google-owned self-driving car company, offers a superior, safe, and stress-free ride experience in Phoenix and San Francisco. It aims to lower costs to compete with Uber, potentially disrupting the ridesharing market.
Merlin Labs aims to test an AI-powered KC-135 within a year
Two startups, Merlin Labs and EpiSci, collaborate to develop self-flying tankers and advanced AI for dogfighting. They aim to create AI pilots to reduce human pilot dependency in Air Force missions.
Traffic engineers build roads relying on outdated research, faulty data
Traffic engineers face criticism for road designs contributing to increased crashes. Larger vehicles heighten risks for pedestrians and cyclists. Experts urge reevaluation of crash data to address systemic issues and promote safer transportation systems.
2 comments> [Y]ou cannot combine accidents with self-driving cars [SAE Level 4] with the accidents of Teslas [SAE Level 2],” said Cummings. She took issue with discussing them in tandem and points out these categories of vehicles operate differently....
> [Level 4 vehicles] were roughly 36 percent less likely to be involved in moderate injury accidents and 90 percent less likely to be involved in a fatal accident. Compared to human-driven vehicles, the risk of rear-end collision was roughly halved, and the risk of a broadside collision was roughly one-fifth. Level 4 AVs were close to one-fifthtieth as likely to run off the road.
> [However] they were over five times more likely to be involved in an accident at dawn and dusk. They were relatively bad at navigating turns as well, with the odds of an accident during a turn almost doubled compared to those for human-driven vehicles.
I assume that the findings in paragraph 2 are despite the limitations from paragraph 3? That makes the "regular driving" performance look even more impressive.
Related
Waymo recalls entire fleet after one hits utility pole
Waymo recalls 672 self-driving vehicles due to a Phoenix incident. The recall addresses software issues related to avoiding poles. Safety improvements aim to build trust as Waymo expands services.
An Anatomy of Algorithm Aversion
The study delves into algorithm aversion, where people favor human judgment over algorithms despite their superior performance. Factors include agency desire, emotional reactions, and ignorance. Addressing these could enhance algorithm acceptance.
Waymo the Leapfrog
Waymo, a Google-owned self-driving car company, offers a superior, safe, and stress-free ride experience in Phoenix and San Francisco. It aims to lower costs to compete with Uber, potentially disrupting the ridesharing market.
Merlin Labs aims to test an AI-powered KC-135 within a year
Two startups, Merlin Labs and EpiSci, collaborate to develop self-flying tankers and advanced AI for dogfighting. They aim to create AI pilots to reduce human pilot dependency in Air Force missions.
Traffic engineers build roads relying on outdated research, faulty data
Traffic engineers face criticism for road designs contributing to increased crashes. Larger vehicles heighten risks for pedestrians and cyclists. Experts urge reevaluation of crash data to address systemic issues and promote safer transportation systems.