Deep reinforcement learning is becoming increasingly popular for robot control algorithms, with the aim for a robot to self-learn useful feature representations from unstructured sensory input leading to the optimal actuation policy. In addition to sensors mounted on the robot, sensors might also be deployed in the environment, although these might need to be accessed via an unreliable wireless connection. In this paper, we demonstrate deep neural network architectures that are able to fuse information generated by multiple sensors and are robust to sensor failures at runtime. We evaluate our method on a search and pick task for a robot both in simulation and the real world.
The increase in available ICT infrastructure in hospitals offers cost reduction opportunities by optimizing various workflows, while maintaining quality of care. In this demonstrator-paper, we present a self-learning dashboard, for monitoring and learning the cause of delays of hospital transports. By identifying these causes, future delays in transport time can be reduced.