Object-Independent Human-to-Robot Handovers using Real Time Robotic Vision
This addresses the challenge of safe and general human-robot handovers for applications like assistive robotics, though it is incremental with improvements in safety and object independence.
The paper tackles the problem of enabling robots to safely take objects from humans without prior knowledge of the objects, using real-time vision and manipulation, achieving an 81.9% success rate in experiments with 13 objects.
We present an approach for safe and object-independent human-to-robot handovers using real time robotic vision and manipulation. We aim for general applicability with a generic object detector, a fast grasp selection algorithm and by using a single gripper-mounted RGB-D camera, hence not relying on external sensors. The robot is controlled via visual servoing towards the object of interest. Putting a high emphasis on safety, we use two perception modules: human body part segmentation and hand/finger segmentation. Pixels that are deemed to belong to the human are filtered out from candidate grasp poses, hence ensuring that the robot safely picks the object without colliding with the human partner. The grasp selection and perception modules run concurrently in real-time, which allows monitoring of the progress. In experiments with 13 objects, the robot was able to successfully take the object from the human in 81.9% of the trials.