Towards reliable and scalable robot communication

Abstract

The Robot Operating System (ROS) is the de facto standard platform for modern robots. However, communication between ROS nodes has scalability and reliability issues in practice. In this paper, we investigate whether Erlang's lightweight concurrency and reliability mechanisms have the potential to address these issues. The basis of the investigation is a pair of simple but typical robotic control applications, namely two face-trackers: one using ROS publish/subscribe messaging, and the other a bespoke Erlang communication framework.We report experiments that compare five key aspects of the ROS and Erlang face trackers. We find that Erlang communication scales better, supporting at least 3.5 times more active processes (700 processes) than its ROS-based counterpart (200 nodes) while consuming half of the memory. However, while both face tracking prototypes exhibit similar detection accuracy and transmission latencies with 10 or fewer workers, Erlang exhibits a continuous increase in the total time taken to process a frame as more agents are added, and we identify the cause. A reliability study shows that while both ROS and Erlang restart failed computations, the Erlang processes restart 1000-1500 times faster than ROS nodes, reducing robot component downtime and mitigating the impact of the failures.

Scaling Reliably

“…This is because processes are recovered within the Virtual machine using (globally synchronised) local recovery information. For example, on a common X86/Ubuntu platform typical Erlang process recovery times are around 0.3ms, so around 1000x less than the Unix process recovery time on the same platform [58]. We have conducted more detailed experiments on an Instant Messenger benchmark, and obtained similar results [23].…”

Reliable distribution of computational load in robot teams

“…Communication between ROS nodes can be publish/subscribe, RPC, or via a global parameter server. As ROS adopts a graph to store and manage node connections, scalability issues arise for large numbers of nodes (Lutac et al 2016). To enhance the scalability and robust-…”