Inspired by the human nature that a child can learn by taking an objectthen observing it, we proposed two novel methods: (1) Object Detection by Interactive Perception (ODIP), where a few-shot object detector gradually learns unseen instances by interacting with a well-developed object grasping system, collecting required visual dataannotations in an automatic manner. (2) an efficienteffective few-shot object detection model with novel attention mechanism called Dual-Awareness Attention (DAnA).

"It is expected that human will work with robots in the coming years. However, it is still unknown how both can collaborate together. Meanwhile, it is still very time-consuming to deploy intelligent robots in production lines. For this work, we investigate deep comprehension for 3D (point cloud)text (voice) signals to enable novel human-robotic object referring for robotic arms. For the task

Multi-axis force/torque sensors are key components of precision machinesrobot arms. Development of the multi-axis force/torque sensor is a popular research topic in Taiwan. This research developed design methods, calibration machinescalibration algorithms for multi-axis force/torque sensors. These efforts contribute the enhancement of precision of 0.20 (1.25 times than commercialize pro

In order to replace humans so as to ensure safety in highly hazardous environments, such as COVID-19 testing sites, a dual-arm humanoid robot has been developed by our NTHU team. This humanoid robot with 7-axis robotic arm, vision system, IMUtouch sensors intelligence is able to imitate human actions intelligently. There are several technologies that were developed for this humanoid robot: robotic arm joints which correspond to human arm joints, a novel multiple-object tracking technology which can distinguish individual occluded objects,a real-time eye-hand calibration technology.