Work

Data-Driven Methods to Build Robust Legged Robots

Year: 2019
Type: dissertation
Abstract: For robots to ever achieve signicant autonomy, they need to be able to mitigate performance loss due to uncertainty, typically from a novel environment or morphological variation of their bodies. Legged robots, with their complex dynamics, are particularly challenging to control with principled theory. Hybrid events, uncertainty, and high dimension are all confounding factors for direct analysis of models. On the other hand, direct data-driven methods have proven to be equally dicult to employ. The high dimension and mechanical complexity of legged robots have proven challenging for hardware-in-the-loop strategies to exploit without signicant eort by human operators. We advocate that we can exploit both perspectives by capitalizing on qualitative features of mathematical models applicable to legged robots, and use that knowledge to strongly inform data-driven methods. We show that the existence of these simple structures can greatly facilitate robust design of legged robots from a data-driven perspective. We begin by demonstrating that the factorial complexity of hybrid models can be elegantly resolved with computationally tractable algorithms, and establish that a novel form of distributed control is predicted. We then continue by demonstrating that a relaxed version of the famous templates and anchors hypothesis can be used to encode performance objectives in a highly redundant way, allowing robots that have suffered damage to autonomously compensate. We conclude with a deadbeat stabilization result that is quite general, and can be determined without equations of motion.
Language: English
Open Access status: green
OpenAlex ID: W4389348669
Cites: 87
Cited by:
Related to: 10