We are focusing on 5G-based cloud robotics use cases.
Repeatedly, it has been emphasized that 5G technology holds significant potential for enhancing cloud robotics in many ways: low-latency, high bandwidth, good coverage, sclable and flexible, network slicing and QoS, edge computing capabilities, etc.
We are focusing on the communication aspects of robot agility.
Agility is a compound notion of reconfigurability and autonomy as opposed to the typical use of automated robots with rigid pre-programmed tasks. Based upon the perceived state of the world, known robot capabilities, and desired goal, the robot should be able to generate plans on its own. This allows for a more autonomous system in the face of errors that may not have been predicted.
The upcoming IEEE P2940 Standard for Measuring Robot Agility provides a listing of desirable traits of robotic systems under the umbrella of agility. In particular, it describes a set of quantitative test methods and metrics for assessing the following ten aspects: hardware reconfigurability, software reconfigurability, communications, task representation, sensing, reasoning, perception, planning, tasking, and execution.
We are focusing on the game-changing potential of AI in cloud robotics.
Artificial Intelligence (AI) and cloud robotics are interconnected. AI empowers robots with intelligent capabilities, while the cloud provides the resources, computational power, and collaborative environment for AI algorithms to run, learn, and share knowledge. The synergy between AI and cloud robotics enables robots to operate with greater autonomy, adaptability, and intelligence (i.e., in a more agile way).
We are focusing on real time data and media exchange between the robot and the cloud components.
While fast network connections are essential, minimizing delay requires consideration of factors beyond just the network itself. Consequently, we employ AI-based predictions as a strategic approach to achieve our real-time goal effectively. In scenarios, like drone or AMR control, with AI-powered predictions as a crucial part of our approach, we can anticipate potential obstacles and actively mitigate them in real-time.
Latency: Since cloud robotics involves offloading computation and data processing to the cloud, the communication delay between the robot and the cloud can introduce significant latency. This delay can impact real-time decision-making and control, particularly in time-critical applications.
Connectivity: Cloud robotics heavily relies on a stable and robust network connection for seamless communication between the robot and the cloud. However, network connectivity can be inconsistent or unreliable in certain environments, especially when wireless radio communication is concerned. Disruptions in connectivity can lead to communication failures and hinder the performance and responsiveness of cloud-connected robots.
Bandwidth: Cloud robotics often involves transmitting large amounts of data between the robot and the cloud, such as sensor data or video streams. Limited bandwidth can pose challenges, especially when dealing with high-resolution video feeds or processing-intensive tasks. Insufficient bandwidth can result in data bottlenecks and increased latency.