YCB-Handovers Dataset: Analyzing Object Weight Impact on Human Handovers to Adapt Robotic Handover Motion

2025-12-23

AI Summary

This study investigates how object weight influences human handover kinematics to enable weight-adaptive, human-like robotic handovers. To address the lack of weight-sensitive handover data, we introduce YCB-Handovers—the first large-scale, weight-annotated dataset of 2,771 human-to-human handovers, captured using high-precision motion capture and YCB-object pose tracking. Through statistical modeling and kinematic analysis, we quantify—on a large scale—how weight modulates reach velocity profiles, timing of acceleration peaks, and pre-handover end-effector posture. Leveraging these findings, we propose a weight-aware motion planning model that significantly improves robotic handover success rate and human acceptability. Our core contributions are: (1) establishing YCB-Handovers as a benchmark dataset for weight–motion coupling in handovers; and (2) introducing a generalizable modeling framework for weight-adaptive handover planning, enabling robots to dynamically adjust motion parameters based on perceived object weight.

Technology Category

• Intelligent Robots: Manipulation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

This paper introduces the YCB-Handovers dataset, capturing motion data of 2771 human-human handovers with varying object weights. The dataset aims to bridge a gap in human-robot collaboration research, providing insights into the impact of object weight in human handovers and readiness cues for intuitive robotic motion planning. The underlying dataset for object recognition and tracking is the YCB (Yale-CMU-Berkeley) dataset, which is an established standard dataset used in algorithms for robotic manipulation, including grasping and carrying objects. The YCB-Handovers dataset incorporates human motion patterns in handovers, making it applicable for data-driven, human-inspired models aimed at weight-sensitive motion planning and adaptive robotic behaviors. This dataset covers an extensive range of weights, allowing for a more robust study of handover behavior and weight variation. Some objects also require careful handovers, highlighting contrasts with standard handovers. We also provide a detailed analysis of the object's weight impact on the human reaching motion in these handovers.

Problem

• Analyzes impact of object weight on human handover motions
• Provides dataset for weight-sensitive robotic motion planning
• Enables adaptive robotic behaviors through human-inspired models

Innovation

• Dataset captures human motion for varied weight handovers
• Enables weight-sensitive robotic motion planning from human data
• Incorporates YCB dataset for object recognition and tracking