Abstract Cooperative perception, the collaborative sensing and interpretation of environmental data by multiple robots, is increasingly vital for deploying heterogeneous unmanned ground and aerial vehicles in unstructured outdoor domains such as forests, agricultural landscapes, and peatlands. Traditional heavy machinery faces accessibility challenges, labour shortages, and ecological impacts including soil compaction. This survey systematically reviews recent advances in cooperative perception tailored to these natural outdoor applications, with a primary focus on forestry and agriculture. First, we propose a comprehensive taxonomy of communication architectures, data-fusion strategies, coordination mechanisms, and decision-making techniques. Second, we delineate exploration and exploitation modes of operation, clarifying their roles in initial mapping and ongoing mission support. Third, we analyse the state-of-the-art in communication-aware planning, semantic and metric mapping, distributed decision processes, and multi-robot task allocation. Our study highlights critical research gaps—such as limited active perception behaviours, underdeveloped communication-aware path planning, insufficient spatial-prediction integration, and scant adoption of metric-semantic representations. Finally, we outline a forward-looking research agenda aimed at enabling robust, adaptive, and environmentally considerate robotic teams capable of real-world deployment. This work serves as a foundational reference for advancing cooperative perception in multi-robot systems for natural environments.
Boralessa et al. (Wed,) studied this question.