Despite promising developments in robotics and automation, we are reliant on humans and single-agent systems for some of the most dangerous scientific tasks on Earth and beyond. Environmental monitoring and sampling of rivers, oceans, and glaciers, spatio-temporal mapping of arctic regions, the characterization of off-Earth planetary environments, and the realization  of space-based astronomy, are but some examples. Heterogeneous teams of robots have the potential to adapt to and thrive in these extreme, unstructured, and dynamic environments. Understanding the mechanisms by which teams of robots can be successfully deployed and autonomously cooperate to assist, augment, and eventually alleviate the need for large groups of humans in these regions is at the forefront of today’s robotics research and technology development. This workshop will bring together a community of roboticists, environmental scientists, machine learning experts, and space researchers with the goal of redefining the state of the art in the field of heterogeneous multi-robot cooperation for exploration and science in extreme environments.