Latest Developments of Gesture Recognition for Human–Robot Collaboration

Abstract

Large Language Models (LLMs) are gaining popularity in the field of robotics. However, LLM-based robots are limited to simple, repetitive motions due to the poor integration between language models, robots, and the environment. This paper proposes a novel approach to enhance the performance of LLM-based autonomous manipulation through Human-Robot Collaboration (HRC). The approach involves using a prompted GPT-4 language model to decompose high-level language commands into sequences of motions that can be executed by the robot. The system also employs a YOLO-based perception algorithm, providing visual cues to the LLM, which aids in planning feasible motions within the specific environment. Additionally, an HRC method is proposed by combining teleoperation and Dynamic Movement Primitives (DMP), allowing the LLM-based robot to learn from human guidance. Real-world experiments have been conducted using the Toyota Human Support Robot for manipulation tasks. The outcomes indicate that tasks requiring complex trajectory planning and reasoning over environments can be efficiently accomplished through the incorporation of human demonstrations.

A Novel Human Intention Prediction Approach Based on Fuzzy Rules through Wearable Sensing in Human–Robot Handover

“…We employed human gestures to represent human handover intentions because they are more advantageous compared to other approaches [ 36 ]. For example, compared with using natural language to represent human handover intentions [ 37 ], using human gestures to represent human handover intentions avoids interference from noise in the industrial environment.…”

“…These intentions include (a) Give the big red cylinder, (b) Give the middle black cylinder, (c) Give the small blue cylinder, (d) Need the big red cylinder, (e) Need the middle black cylinder, (f) Need the small blue cylinder, (g) Rotate arm, (h) Rotate hand, (i) Move up, (j) Move down, (k) Move close, and (l) Move far. We employed human gestures to represent human handover intentions because they are more advantageous compared to other approaches [36]. For example, compared with using natural language to represent human handover intentions [37], using human gestures to represent human handover intentions avoids interference from noise in the industrial environment.…”