BEIJING, July 20 (Xinhua) — The following is a summary of published science and technology news of China.

AI TO BETTER UNDERSTAND HUMAN EXPECTATIONS

A research team has proposed an artificial intelligence (AI) system in which robots not only serve as listeners but also speakers, providing an opportunity for AI to better understand human expectations.

In this AI system, a group of robots predicted human intents by taking in situ feedback into consideration while explaining their decision-making processes to humans, forming a bidirectional relationship, according to the study findings published in the journal Science Robotics.

The findings showed that real-time mutual understanding between humans and robots in complex tasks was achievable with a learning model based on bidirectional communication.

SOFT ROBOT TO ABSORB MICROPLASTICS

Chinese scientists have developed a fish-shaped light-actuated swimming robot that can “eat” microplastics in water bodies and repair itself if damaged.

Inspired by nacre, a strong, durable and flexible material obtained from hard clam shells, scientists from Sichuan University modeled nacre’s graphene-based gradient nanostructure to create a durable, flexible and self-repairing nanocomposite, according to a study published in the journal Nano Letters.

The research team then used the new material to develop a 15-millimeter fish-like soft robot, enabling it to swim rapidly and absorb microplastics in the oceans, which breaks the mutual exclusion of soft robot function execution and fast drive.

THERAPEUTIC TARGETS FOR ALS

Using an artificial intelligence (AI) platform, an international research team has identified more than two dozen new targets with therapeutic potential for amyotrophic lateral sclerosis (ALS), according to a recent study.

Researchers from Harvard Medical School, Johns Hopkins School of Medicine, China’s Tsinghua University, alongside drug discovery company Insilico Medicine, used Insilico’s AI-driven target discovery engine, called PandaOmics, to identify 17 high-confidence and 11 novel therapeutic targets for the disease.

In animal models, the team validated that 18 of the 28 identified gene targets were functionally correlated to the ALS and found that in eight of them, suppression could strongly reduce neurodegeneration.