We propose a technique for depth completion of transparent objects using augmented data captured directly from real environments with complicated geometry. Using cyclic adversarial learning we train translators to convert between painted versions of the objects and their real transparent counterpart. The translators are trained on unpaired data, hence datasets can be created rapidly and without any manual labeling. Our technique does not make any assumptions about the geometry of the environment, unlike SOTA systems that assume easily observable occlusion and contact edges, such as ClearGrasp. We show how our technique outperforms ClearGrasp in a dishwasher environment, in which occlusion and contact edges are difficult to observe. We also show how the technique can be used to create an object manipulation application with a humanoid robot. Supplementary URI: https://ftorise.github.io/faking_depth_web/.

When humans see a scene, they can roughly imagine the forces applied to objects based on their expe-rience and use them to handle the objects properly. This paper considers transferring this “force-visualization” ability to robots. We hypothesize that a rough force distribution (named “force map”) can be utilized for object manipulation strategies even if accurate force estimation is impossible. Based on this hypothesis, we propose a training method to predict the force map from vision. To investigate this hypothesis, we generated scenes where objects were stacked in bulk through simulation and trained a model to predict the contact force from a single image. We further applied domain randomization to make the trained model function on real images. The experimental results showed that the model trained using only synthetic images could predict approximate patterns representing the contact areas of the objects even for real images. Then, we designed a simple algorithm to plan a lifting direction using the predicted force distribution. We confirmed that using the predicted force distribution contributes to finding natural lifting directions for typical real-world scenes. Furthermore, the evaluation through simulations showed that the disturbance caused to surrounding objects was reduced by 26 % (translation displacement) and by 39 % (angular displacement) for scenes where objects were overlapping.

The education of children with Autism Spectrum Disorder (ASD) to acquire concepts present in social interaction is essential for facilitating their inclusion in society. This paper proposes a novel portable device to digitalize sessions and provide Visual Support (VS) to aid children during their learning process. The device can record video and estimate the pose of participants during activities, which can be used for further analysis. It uses fisheye lenses for sensing and projecting and a new concept, called Panda Masking, to minimize light illumination on participants’ eyes. Initial tests with the device indicate its feasibility to be used in monitoring therapy sessions and provide Visual Support while preventing face illumination.

It is well-known that walking offers many health benefits for everyone, especially for older people who need to maintain mobility and independence coping with declining of functional capacity. In this paper, we present the design of a humanoid walking trainer that has to monitor and encourage walking in the elderly. This design is based on our target users' preferences. We present as well a preliminary walking experiment that was carried out in order to test the accuracy of the gait data obtained from the laser range sensor, which is positioned on the robot, during motion.