DIJIT: A Robotic Head for an Active Observer

2025-12-08

AI Summary

Existing models of human eye–head coordination in active vision research lack sufficient biomimetic fidelity. Method: We designed and implemented DIJIT, a highly biomimetic binocular robotic head featuring nine mechanical degrees of freedom (DOFs) and four optical DOFs—enabling human-like oculomotor behaviors including vergence, version, and cyclotorsion. We further proposed a direct pose-to-motor-parameter mapping strategy for saccadic control, achieving human-level accuracy (±0.5°) and speed (peak angular velocity >300°/s). Contribution/Results: Integrated with high-fidelity mechanics and a dual-camera active vision system, DIJIT empirically validates the functional advantages of eye–head coordination in stereo matching and target tracking. It provides a reproducible hardware platform and a novel control paradigm for biologically inspired active vision modeling and comparative analysis of human–machine visual processing differences.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Manipulation
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

We present DIJIT, a novel binocular robotic head expressly designed for mobile agents that behave as active observers. DIJIT's unique breadth of functionality enables active vision research and the study of human-like eye and head-neck motions, their interrelationships, and how each contributes to visual ability. DIJIT is also being used to explore the differences between how human vision employs eye/head movements to solve visual tasks and current computer vision methods. DIJIT's design features nine mechanical degrees of freedom, while the cameras and lenses provide an additional four optical degrees of freedom. The ranges and speeds of the mechanical design are comparable to human performance. Our design includes the ranges of motion required for convergent stereo, namely, vergence, version, and cyclotorsion. The exploration of the utility of these to both human and machine vision is ongoing. Here, we present the design of DIJIT and evaluate aspects of its performance. We present a new method for saccadic camera movements. In this method, a direct relationship between camera orientation and motor values is developed. The resulting saccadic camera movements are close to human movements in terms of their accuracy.

Problem

• Design a robotic head for active vision research
• Study human-like eye and head-neck motion relationships
• Compare human vision with computer vision methods

Innovation

• Binocular robotic head with nine mechanical degrees of freedom
• Cameras and lenses provide four optical degrees of freedom
• Direct relationship between camera orientation and motor values