Robotics

A new training strategy enables robots to efficiently collaborate and learn in dynamic environments, improving their performance in real-world tasks.

The innovative integration of robotics and machine learning accelerates the development of efficient, sustainable hydrogen catalysts.

A new transparent soft robot uses innovative materials to blend into underwater environments by mimicking the moon jellyfish’s movement and appearance.

A pioneering computational framework empowers robots to acquire, recognise and effectively use previously unseen tools.

A*STAR researchers introduce Pholus, a first-of-its-kind robot that senses its environment in real-time and bypasses obstacles with unprecedented agility.

A novel machine learning framework makes it faster and easier to train robots that can perform tasks with unprecedented precision.

A fresh design approach to high-performing variable-stiffness rotating joints could enable humans to work safely alongside robots in industrial manufacturing environments.

A deep learning technique developed by A*STAR researchers uses WiFi data to help robots find their way around.

By breaking complex actions into their basic components, researchers have developed a versatile framework that enables robots to learn from human demonstrators.

Horizontal Technology Programme Offices will bring A*STAR’s deep capabilities to bear on real-world issues facing Singapore and the wider world, says Deputy Chief Executive (Research), Andy Hor.

Researchers at A*STAR have designed a hybrid machine learning model to enhance touch capabilities in robots.

An algorithm gives robots an instinctive understanding of how to use tools