Evaluating Robots Like Human Infants: A Case Study of Learned Bipedal Locomotion

TL;DR

This study applies developmental psychology methods to systematically analyze how different training regimens affect the learned bipedal walking behaviors of a simulated robot, offering insights comparable to infant development studies.

Contribution

It introduces a novel interdisciplinary approach combining developmental psychology and robotics to systematically evaluate training effects on robot behavior development.

Findings

Training regimens significantly influence Cassie's walking behaviors.

Simulated experiments reveal parallels between robot learning and infant development.

Insights inform future systematic testing of training impacts on complex behaviors.

Abstract

Typically, learned robot controllers are trained via relatively unsystematic regimens and evaluated with coarse-grained outcome measures such as average cumulative reward. The typical approach is useful to compare learning algorithms but provides limited insight into the effects of different training regimens and little understanding about the richness and complexity of learned behaviors. Likewise, human infants and other animals are "trained" via unsystematic regimens, but in contrast, developmental psychologists evaluate their performance in highly-controlled experiments with fine-grained measures such as success, speed of walking, and prospective adjustments. However, the study of learned behavior in human infants is limited by the practical constraints of training and testing babies. Here, we present a case study that applies methods from developmental psychology to study the learned behavior of the simulated bipedal robot Cassie. Following research on infant walking, we systematically designed reinforcement learning training regimens and tested the resulting controllers in simulated environments analogous to those used for babies--but without the practical constraints. Results reveal new insights into the behavioral impact of different training regimens and the development of Cassie's learned behaviors relative to infants who are learning to walk. This interdisciplinary baby-robot approach provides inspiration for future research designed to systematically test effects of training on the development of complex learned robot behaviors.