No abstract

We present an approach for safe and objectindependent 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.

No abstract

The study objective is to test general-and sport-specific adaption during a single training on the Flexibility Trainer. The device is designed to trigger residual muscle tone decreases of the hip-joint muscles by providing (nearly) isokinetic resistance during a full range of motion strength training in adduction/abduction and flexion/ extension direction. Static hip flexion and abduction as well as kinematics of double side kicks were analysed on 15 participants before and after training (or rest for controls) to assess general flexibility and sport-specific movement range. Tests were recorded by a Vicon® motion capturing system. Static hip flexion and abduction as well as leg vector spreading angles (VSA) at different nodes of the kick were selected to determine adaptions of active and passive flexibility. Normalised hip joint moments, movement velocities and VSA were calculated to evaluate the training with the device. ANOVAs with 4-repeated measures and Friedman tests were performed to identify time differences and Bonferroni post-hoc test to identify betweensubject effects. Significant differences were found for both static flexibility tests (Flexion = 13.65%; Abduction = 9.94%) and the VSA at specific action phases (≤15.15%). Results indicate that short-term adaptions when training with the Flexibility Trainer are exceeding comparable literature showing improved flexibility and sportspecific performance.

No abstract