Robots are integrating more huge-size models to enrich functions and improve accuracy, which leads to out-of-control computing pressure. And thus robots are encountering bottlenecks in computing power and battery capacity. Fog or cloud robotics is one of the most anticipated theories to address these issues. Approaches of cloud robotics have developed from system-level to node-level. However, the present node-level systems are not flexible enough to dynamically adapt to changing conditions. To address this, we present ElasticROS, which evolves the present node-level systems into an algorithm-level one. ElasticROS is based on ROS and ROS2. For fog and cloud robotics, it is the first robot operating system with algorithm-level collaborative computing. ElasticROS develops elastic collaborative computing to achieve adaptability to dynamic conditions. The collaborative computing algorithm is the core and challenge of ElasticROS. We abstract the problem and then propose an algorithm named ElasAction to address. It is a dynamic action decision algorithm based on online learning, which determines how robots and servers cooperate. The algorithm dynamically updates parameters to adapt to changes of conditions where the robot is currently in. It achieves elastically distributing of computing tasks to robots and servers according to configurations. In addition, we prove that the regret upper bound of the ElasAction is sublinear, which guarantees its convergence and thus enables ElasticROS to be stable in its elasticity. Finally, we conducted experiments with ElasticROS on common tasks of robotics, including SLAM, grasping and human-robot dialogue, and then measured its performances in latency, CPU usage and power consumption. The algorithm-level ElasticROS performs significantly better than the present node-level system.

翻译：机器人正集成更多大规模模型以丰富功能并提升精度，这导致计算压力失控，进而使机器人在算力和电池容量方面遭遇瓶颈。雾计算或云计算机器人是解决该问题最受期待的理论之一。云机器人的方法已从系统级发展到节点级。然而，现有节点级系统在动态适应条件变化方面缺乏灵活性。为此，我们提出ElasticROS，将现有节点级系统升级为算法级系统。ElasticROS基于ROS和ROS2开发，是首个面向雾与云机器人的算法级协作计算操作系统。ElasticROS通过弹性协作计算实现对动态条件的适应性，其中协作计算算法是核心与挑战。我们对问题进行抽象，并提出名为ElasAction的算法。该算法是一种基于在线学习的动态动作决策算法，用于决定机器人与服务器如何协作，通过动态更新参数以适应机器人当前所处环境的变化，并根据配置将计算任务弹性分配给机器人和服务器。此外，我们证明ElasAction的遗憾上界呈次线性，这保证了其收敛性，从而使ElasticROS在弹性方面保持稳定。最后，我们使用ElasticROS在机器人常见任务（包括SLAM、抓取和人机对话）上进行实验，并测量其在延迟、CPU使用率和功耗方面的性能。实验表明，算法级ElasticROS的性能显著优于现有节点级系统。