Researchers have developed a new approach to boosting self-driving vehicle algorithms that could significantly reduce the time and cost required to prepare auto
mated vehicles for real-world deployment, according to the University of Michigan.
Rather than relying on the vast amounts of routine driving data typically used to train autonomous systems, the method focuses on “near-miss” scenarios—rare but safety-critical events that challenge vehicle decision-making.
By generating and prioritizing the high-value training situations in simulation, the framew
ork helps autonomous driving systems learn more efficiently while improving their ability to respond to complex traffic conditions, the researchers said.
The team tested their approach, incorporating both safety-critical and near-miss scenarios, achieving a 90% improvement in the vehicle’s safety performance.
Watch More Image Part 2 >>>
The work builds on the University of Michigan’s testing and validation of connected and automated vehicles, including its use of artificial intelligence (AI) to reduce testing miles required by 99.9%.
The research was funded in part by the National Science Foundation and the Center for Connected and Automated Transportation at U-M, and published earlier this year in Nature Communications.
Citing a 1927 Supreme Court opinion (Robins Dry Dock & Repair Co. v. Flint), Bredar found that th
e public and private entities that have sued are precluded from recovering economic losses resulting from physical damage to the Key Bridge because they had no proprietary interest in the bridge or other property.
Instead, Dali owner Grace Ocean Private Ltd. and operator Synergy Marine Group can only be held liable for economic losses if there was damage to property owned by the claimant.
In keeping with the Robins precedent, the city may pursue its claim related to alleged damage to the 72-inch water main below the river and the county may proceed to try to prove it has a proprietary interest in damaged waterways and shorelines. Also, four cargo damage claims may proceed.
