Professor Daehyung Park’s research team in the School of Computing develops DiSPo, a robot AI model that can flexibly improve task precision from only coarse (low-frequency) demonstrations

DiSPo demonstrates up to an 81% higher success rate than existing technologies and achieves ultra-precise control in real-world robot experiments, successfully passing through a narrow 2.5 mm clearance

The technology is expected to expand the application of robots in industrial automation fields requiring high dexterity, such as micro-component assembly, medical robotics, and precision machining

On active road construction sites, warning alarms, passing traffic and moving equipment are a constant presence throughout the workday. Over time, those sights and sounds can begin to fade into the background.

When workers encounter the same hazards day after day, they can become desensitized, said Dr. Namgyun Kim, an assistant professor in the Department of Construction Science at Texas A&M University. Workers may begin to tune out the flashing warnings and beeping alarms to focus on the task at hand.

“That is the moment that accidents happen,” said Kim, a leading researcher focused on improving construction safety and productivity through virtual reality, augmented reality and artificial intelligence.

At his Safety Systems.AI Lab, Kim collaborates with Dr. Brian Anderson, who leads the Learning and Attention Lab, to study how workers perceive and respond to hazards using these advanced technologies to develop systems to improve workplace safety and reduce injuries. Through a series of studies involving virtual reality simulations, brain activity monitoring, field observations and AI-driven augmented reality systems, Kim’s work examines whether immersive, experience-based training can help workers maintain attention to hazards in both controlled environments and active work zones.

Researchers have developed a self-driving chemistry lab that can autonomously search through hundreds of catalyst recipes and reaction conditions to identify faster, more selective, and more programmable ways to make important industrial chemicals. The work could accelerate catalyst discovery for industries ranging from pharmaceuticals and plastics to fuels and specialty chemicals.

Gleanmer is a new system that can construct detailed 3D maps of a robot’s environment at high speed while operating at extremely low power. The advance could enable tiny devices to avoid obstacles and safely navigate in the real world.