Implementation of robotic writing ability is recognized as a di±cult task, which involves complicated image processing and robotic control algorithms. This paper introduces a novel approach to robotic writing by using human-robot interactions. The method applies a motion sensing input device to capture a human demonstrator's arm trajectories, uses a gesture determination algorithm to extract a Chinese character's strokes from these trajectories, and employs noise¯ltering and curve¯tting methods to optimize the strokes. The approach displays real-time captured trajectories to the human demonstrator; therefore, the human demonstrator is able to adjust his/her gesture to achieve a better character writing e®ect. Then, our robot writes the human-gestured character by using the robotic arm's joint values. The inverse kinematics algorithm generates the joint values from the stroke trajectories. Experimental analysis shows that the proposed approach can allow a human to naturally and conveniently control the robot in order to write many Chinese characters. Additionally, this approach allows the robot to achieve a satisfactory writing quality for characters with a simple structure, with the potential to write more complex characters.

No abstract

Road detection is a fundamental component of autonomous driving systems since it provides valid space and candidate regions of objects for driving decision. The core of road detection methods is extracting effective and discriminative features. Since two-dimensional (2D) and 3D features are complementary, the authors propose a robust multi-feature combination and optimisation framework for stereo image pairs, called Feature++. First, several 2D and 3D features such as Gabor and plane are, respectively, extracted after the generation of 2D super-pixel and a 3D depth image from stereo matching. Second, the combined features are fed into a three-layer shallow neural network classifier to decide whether a super-pixel is road region or not. Finally, the classified results are further refined using fully connected conditional random field (CRF), taking the content information into consideration. We extensively evaluate the performance of four 2D features, four 3D features, and their combinations. Experiments conducted on the KITTI ROAD benchmark show that (i) the combinations of 2D and 3D features greatly improve the road detection performance and (ii) using CRF as a refinement step is necessary. Overall, their proposed 'Feature + +' method outperforms most manually designed features, and is comparable with state-of-the-art methods that are based on deep learning methods.