MARVIN: Multimodally Advantaged Robotic Vehicle for Improved Navigation

Abstract

Hybrid robots leverage the advantages of multiple types of locomotion. More specif- ically, wheel-legged hybrid robots aim to capture the speed, stability, and power

efficiency of wheeled robots as well as the ability to traverse robust natural terrain

that legged robots provide. Effective hybrid designs are able to capitalize on both sets

of advantages without compromising the overall effectiveness of the machine. Here,

we present a design and implementation of MARVIN, a wheel-legged hybrid robot

that emphasizes three key features: a quick transition mechanism, a well-defined

wheel and leg mode, and the capacity for flexible control through continuously vari- able leg length. We demonstrate how the two clearly defined modes of legs/wheels

in MARVIN capitalize on their respective advantages. Furthermore, in realizing the

tradeoff between modes specific to this robot, we derive a hybrid path-planning algo- rithm using an empirically driven cost function, which we found by collecting data in

real-terrain experiments. We discuss our mechanical, electronic, and software design

approaches in building a prototype of the proposed design. We also review our ex- perimental methods. Lastly, we point out lessons learned from the operation of our

prototype robot, identifying directions for future upgrades.