Tuesday, June 10, 2025

HKUST Engineering School introduces human-like driving technology for autonomous vehicles

Reducing overall traffic risk by 26.3%

Hong Kong University of Science and Technology

Prof. YANG Hai & LU Hongliang — image:
Prof. YANG Hai (right), Chair Professor of the Department of Civil and Environmental Engineering at HKUST, and his PhD student LU Hongliang (left) from the Intelligent Transportation Thrust at HKUST(GZ), draw inspiration from neuroscience, human cognitive processes, and ethics to enable self-driving cars to “think” like human drivers.
view more
Credit: HKUST

Self-driving cars will soon be able to “think” like human drivers under complex traffic environments, thanks to a groundbreaking cognitive encoding framework built by a multidisciplinary research team from the School of Engineering at the Hong Kong University of Science and Technology (HKUST). This innovation significantly enhances the safety of autonomous vehicles (AVs), reducing overall traffic risk by 26.3% and cutting potential harm to high-risk road users such as pedestrians and cyclists by an impressive 51.7%. Even the AVs themselves benefited, with their risk levels lowered by 8.3%, paving the way for a new framework to advance the automation of vehicle safety.

Existing AVs have one common limitation: their decision-making systems can only make pairwise risk assessments, failing to holistically consider interactions among multiple road users. This contrasts with a proficient driver who, for example, can skillfully navigate an intersection by prioritizing pedestrian protection while slightly compromising the safety of nearby vehicles. Once pedestrians are confirmed to be safe, the driver can then shift focus to nearby vehicles. Such risk management ability exhibited by humans is known as “social sensitivity”.

To empower AVs with social sensitivity, a research team led by Prof. YANG Hai, Chair Professor of the Department of Civil and Environmental Engineering at HKUST, drew inspiration from neuroscience, human cognitive processes, and ethics to develop a human-plausible cognitive encoding scheme. This system enables AVs to perceive, evaluate, and behave in a way resembling a thoughtful human driver.

This novel system integrates three innovative features:

Individual Risk Assessment – Evaluates the risk faced by each road user, including pedestrians, cyclists, motorcyclists, and nearby vehicles. This involves assessing their speed, distances from one another, and behavioral predictability. For example, a child walking near the road would be considered high risk.
Socially Weighted Risk Mapping – Adds an ethical layer to decision-making by prioritizing vulnerable participants’ safety. In practice, it means the AV might yield to a pedestrian even when technical rules allow it to proceed.
Behavioral Belief Encoding – Predicts how the AV’s actions will affect the overall traffic situation. For instance, it considers whether a quick lane change might cause nearby drivers to brake suddenly or increase congestion.

To determine the safety performance of this cognitive encoding scheme, the research team evaluated the new framework using 2,000 benchmark traffic scenarios, and the results showed that the framework reduced overall traffic risk by 26.3%. Remarkably, these safety improvements came with better operational efficiency. In the abovementioned simulations, AVs equipped with this system completed driving tasks 13.9% faster on average, demonstrating that ethical driving and performance can go hand in hand.

“By emulating the human capacity for holistic risk processing and moral reasoning, we enable AVs to behave more responsibly in ethically ambiguous situations, such as congested intersections or near schools,” said Prof. Yang.

“Our framework is designed to be flexible and adaptable to meet different regulations and social norms. For example, while some countries prioritize protecting vulnerable road users, others place greater emphasis on traffic flow efficiency.” Prof. Yang added, “Additionally, legal interpretations of accident liability vary across jurisdictions. Our system can adjust weightings, enabling AVs to drive like locals and making global deployment more feasible.”

This pioneering study was conducted in collaboration with Hong Kong University of Science and Technology (Guangzhou), Southeast University, Beijing Institute of Technology, Tsinghua University, Tongji University, and the University of Washington. The full paper, titled “Empowering Safer Socially Sensitive Autonomous Vehicles Using Human-Plausible Cognitive Encoding”, was recently published in the prestigious journal Proceedings of the National Academy of Sciences (PNAS).

As the next step, the research team is developing a large-scale dataset representing diverse regional driving patterns and social expectations. They are also in discussion with potential collaborators to support future integration and testing efforts.

Journal

Proceedings of the National Academy of Sciences

DOI

10.1073/pnas.2401626122

Method of Research

Experimental study

Subject of Research

Not applicable

Article Title

Empowering safer socially sensitive autonomous vehicles using human-plausible cognitive encoding

The proposed framework for socially sensitive AVs
Prof. YANG Hai (right) discusses the research framework with LU Hongliang (left), the first author of the study.
Credit
HKUST

Scientists reveal gene pairs conferring resistance to wheat diseases

Chinese Academy of Sciences Headquarters

The cloning of powdery mildew resistance gene Pm26 and stripe rust resistance gene YrTD121 from wild emmer wheat (Triticum dicoccides) and their breeding application — image:
The cloning of powdery mildew resistance gene *Pm26* and stripe rust resistance gene *YrTD121* from wild emmer wheat (*Triticum dicoccides*) and their breeding application
view more
Credit: IGDB

A research team led by Prof. LIU Zhiyong at the Institute of Genetics and Developmental Biology of the Chinese Academy of Sciences has identified two novel genetic mechanisms for disease resistance in wheat, offering promising strategies to enhance resilience against powdery mildew and stripe rust. The discoveries were published in back-to-back articles in Nature Genetics on June 9.

The studies reveal that both the powdery mildew resistance locus MlIW170 (also known as Pm26) and the stripe rust resistance locus YrTD121—both derived from wild emmer wheat (Triticum dicoccoides)—are governed not by single genes but by pairs of genes that encode nucleotide-binding leucine-rich repeat (NLR) immune receptors. These gene pairs represent an atypical architecture in plant immunity and offer new insights into the evolution and function of disease resistance mechanisms in crops.

In the powdery mildew study, the researchers used map-based cloning and PacBio HiFi long-read sequencing to identify TdCNL1 and TdCNL5—a genetically linked pair of NLR genes responsible for the resistance conferred by the Pm26 locus. TdCNL1 encodes an NLR protein with a novel potassium-dependent sodium-calcium exchanger (NCKX) integrated domain, while TdCNL5 encodes a canonical coiled-coil NLR (CNL). Functional assays, including mutagenesis and virus-induced gene silencing, confirmed that both genes are essential for resistance. Notably, transgenic wheat lines expressing both genes—or TdCNL1 alone—were resistant, whereas lines expressing only TdCNL5 remained susceptible.

Similarly, in the stripe rust study, the team identified a head-to-head–oriented gene pair, TdNLR1 and TdNLR2, underlying the YrTD121 disease resistance locus. TdNLR1 encodes a canonical NLR protein, while TdNLR2 lacks the typical coiled-coil domain. Despite their structural differences, both genes were found to be indispensable for resistance, as demonstrated through mutagenesis, gene silencing, CRISPR editing, and transgenic experiments. Interestingly, neither gene contains integrated effector-recognition domains, suggesting a distinct and previously uncharacterized NLR configuration. Moreover, the coiled-coil domain of TdNLR1 was shown to self-associate and trigger cell death in planta—a hallmark of immune activation.

Wild emmer wheat, the ancestor of modern bread wheat, has accumulated rich genetic variation through long-term adaptation to complex environments. However, the MlIW170/Pm26 and YrTD121 loci from wild emmer wheat are found in only a few wild emmer wheat populations and were not part of the domestication or evolution of bread wheat. The researchers have developed high-yielding, disease-resistant germplasms with MlIW170/Pm26 and YrTD121 by crossing wild emmer wheat with high-yielding bread wheat varieties and performing continuous backcrossing with marker-assisted selection.

These findings offer crucial disease resistance gene resources and a theoretical basis for breeding broad-spectrum and multi-disease–resistant wheat varieties.