Can we stabilize an inverted pendulum with feedback from a time-of-flight camera?

2026-06-08

AI Summary

This study investigates whether low-cost, low-resolution time-of-flight (ToF) cameras can provide sufficiently accurate state feedback for fast, unstable dynamical systems. Focusing on the classic non-stationary control problem of the inverted pendulum, the authors design a real-time feedback controller that leverages noisy ToF depth measurements and integrates principles from classical control theory to stabilize the system. Their experiments demonstrate, for the first time, that even under conditions of low spatial resolution and high measurement noise, inexpensive ToF cameras can support high-precision balancing control. This finding challenges the prevailing assumption that such sensors lack the requisite accuracy for demanding control tasks and substantiates their practical viability in high-speed, unstable systems.

Abstract

Time-of-flight cameras are popular in robotics for providing direct depth information while being compact, inexpensive, and robust to lighting conditions, but their low spatial resolution and depth noise are widely believed to preclude precise feedback control. In this paper, we show that an inexpensive, low-resolution time-of-flight camera provides sufficient feedback to reliably and precisely balance an inverted pendulum on a cart--a canonical benchmark for fast, unstable dynamics.

Problem

• inverted pendulum
• time-of-flight camera
• feedback control
• depth noise
• low spatial resolution

Innovation

• time-of-flight camera
• inverted pendulum
• feedback control
• low-resolution sensing
• robotics