Modern robots are highly capable in predictable environments, but often struggle in unstructured environments like granular media. However, loose terrains and granular environments are ubiquitous in our world, and improving mobility in these environments would open doors to applications in marine and space exploration, geotechnics, disaster response, and agriculture. In this dissertation, I introduce my work which has utilized models of complex substrate, as well as biomechanical models, to inform the design of novel robotic implementations. I first present my work on extending Granular Resistive Force Theory (RFT) to three dimensions, which enables rapid force estimations of intrusions in granular media. I then discuss one example of an application of such models to robotic prototypes, through simulations of folding origami feet for horizontal burrowing. I then introduce our mole crab-inspired robot EMBUR (EMerita BUrrowing Robot), the first legged robot to self-burrow in granular media. Two design iterations are introduced, which both serve as prototypes for exploring the physical principles of legged burrowing. Lastly, I present demonstrations of tethered robotic teams in the field, and show how leveraging contact between the tether and natural objects can enable forceful maneuvers, even in complex terrains. I conclude with a discussion of how the techniques introduced can be extended to better inform robot design and control in future work.