Autonomous navigation for BigDog

TLDR

BigDog is a four‑legged robot with exceptional rough‑terrain mobility. The paper equips BigDog with laser scanning, stereo vision, and navigation algorithms, and details the hardware and software implementation while summarizing performance. Using these sensors and algorithms, BigDog performs autonomous navigation to goal positions in unstructured forest environments, perceiving obstacles such as trees, boulders, and ground features, and steering to avoid them. During field tests in unstructured wooded terrain, BigDog reached its goal position 23 of 26 runs and traveled over 130 meters at a time without operator involvement.

Abstract

BigDog is a four legged robot with exceptional rough-terrain mobility. In this paper, we equip BigDog with a laser scanner, stereo vision system, and perception and navigation algorithms. Using these sensors and algorithms, BigDog performs autonomous navigation to goal positions in unstructured forest environments. The robot perceives obstacles, such as trees, boulders, and ground features, and steers to avoid them on its way to the goal. We describe the hardware and software implementation of the navigation system and summarize performance. During field tests in unstructured wooded terrain, BigDog reached its goal position 23 of 26 runs and traveled over 130 meters at a time without operator involvement.