Standing Tall: Sim to Real Fall Classification and Lead Time Prediction for Bipedal Robots

TL;DR

This paper presents a real-time fall prediction system for bipedal robots, achieving high accuracy, low false positives, and significant lead time, validated on the Digit robot with improvements over previous methods.

Contribution

It extends a fall prediction algorithm to real-time hardware and simulation, improving robustness and performance in practical bipedal robot deployment.

Findings

Zero false positive rate in real-time fall prediction

Average lead time of 1.1 seconds, exceeding minimum requirements

High recovery rate of 0.97 in real-world tests

Abstract

This paper extends a previously proposed fall prediction algorithm to a real-time (online) setting, with implementations in both hardware and simulation. The system is validated on the full-sized bipedal robot Digit, where the real-time version achieves performance comparable to the offline implementation while maintaining a zero false positive rate, an average lead time (defined as the difference between the true and predicted fall time) of 1.1s (well above the required minimum of 0.2s), and a maximum lead time error of just 0.03s. It also achieves a high recovery rate of 0.97, demonstrating its effectiveness in real-world deployment. In addition to the real-time implementation, this work identifies key limitations of the original algorithm, particularly under omnidirectional faults, and introduces a fine-tuned strategy to improve robustness. The enhanced algorithm shows measurable improvements across all evaluated metrics, including a 0.05 reduction in average false positive rate and a 1.19s decrease in the maximum error of the average predicted lead time.