Navigation in cluttered underwater environments is challenging, especially when there are constraints on communication and self-localisation, and there is clutter in the environment. In this paper, we first studied the connection between everyday activity of dog walking and the cooperative underwater obstacle avoidance problem. Inspired by this analogy, we propose a novel dog walking paradigm and implement it in a multi-agent underwater system. Simulations were conducted across various scenarios, with performance benchmarked against traditional methods utilising Image-Based Visual Servoing in a multi-agent setup. The results indicate that our dog-walking-inspired paradigm significantly enhances cooperative behavior between agents and outperforms the existing approach in navigating through obstacles.