Internet of Robotic Things: Current Technologies, Applications, Challenges and Future Directions

Nowadays, the Internet of Things (IoT) concept is gaining more and more notoriety bringing the number of connected devices to reach the order of billion units. Its smart technology is influencing the research and developments of advanced solutions in many areas. This paper focuses on the merger between the IoT and robotics named the Internet of Robotic Things (IoRT). Allowing robotic systems to communicate over the internet at a minimal cost is an important technological opportunity. Robots can use the cloud to improve the overall performance and for offloading demanding tasks. Since communicating to the cloud results in latency, data loss, and energy loss, finding efficient techniques is a concern that can be addressed with current machine learning methodologies. Moreover, the use of robotic generates ethical and regulation questions that should be answered for a proper coexistence between humans and robots. This paper aims at providing a better understanding of the new concept of IoRT with its benefits and limitations, as well as guidelines and directions for future research and studies.

Belief-Grounded Networks for Accelerated Robot Learning under Partial Observability

Many important robotics problems are partially observable in the sense that a single visual or force-feedback measurement is insufficient to reconstruct the state. Standard approaches involve learning a policy over beliefs or observation-action histories. However, both of these have drawbacks; it is expensive to track the belief online, and it is hard to learn policies directly over histories. We propose a method for policy learning under partial observability called the Belief-Grounded Network (BGN) in which an auxiliary belief-reconstruction loss incentivizes a neural network to concisely summarize its input history. Since the resulting policy is a function of the history rather than the belief, it can be executed easily at runtime. We compare BGN against several baselines on classic benchmark tasks as well as three novel robotic touch-sensing tasks. BGN outperforms all other tested methods and its learned policies work well when transferred onto a physical robot.