Optimal byzantine resilient convergence in oblivious robot networks

TL;DR

This paper establishes the fundamental limits and proposes a deterministic algorithm for achieving Byzantine-resilient convergence in oblivious robot networks, considering various synchrony models and optimal bounds.

Contribution

It provides necessary and sufficient conditions for convergence with Byzantine robots and introduces an optimal, cautious, deterministic algorithm for different synchrony settings.

Findings

Convergence is possible with Byzantine robots under specific conditions.

The proposed algorithm tolerates f Byzantine robots in optimal network sizes.

Bounds are proven to be optimal for cautious algorithms.

Abstract

Given a set of robots with arbitrary initial location and no agreement on a global coordinate system, convergence requires that all robots asymptotically approach the exact same, but unknown beforehand, location. Robots are oblivious-- they do not recall the past computations -- and are allowed to move in a one-dimensional space. Additionally, robots cannot communicate directly, instead they obtain system related information only via visual sensors. We draw a connection between the convergence problem in robot networks, and the distributed \emph{approximate agreement} problem (that requires correct processes to decide, for some constant $\epsilon$, values distance $\epsilon$ apart and within the range of initial proposed values). Surprisingly, even though specifications are similar, the convergence implementation in robot networks requires specific assumptions about synchrony and Byzantine resilience. In more details, we prove necessary and sufficient conditions for the convergence of mobile robots despite a subset of them being Byzantine (i.e. they can exhibit arbitrary behavior). Additionally, we propose a deterministic convergence algorithm for robot networks and analyze its correctness and complexity in various synchrony settings. The proposed algorithm tolerates f Byzantine robots for (2f+1)-sized robot networks in fully synchronous networks, (3f+1)-sized in semi-synchronous networks. These bounds are optimal for the class of cautious algorithms, which guarantee that correct robots always move inside the range of positions of the correct robots.