Vision-Guided Cooperative Manipulation Framework for Synchronized Grasping and Transport of Cylindrical Objects Using Dual Mobile Manipulators

Despite advances in cooperative mobile manipulation, reports on low-cost frameworks that enable dual-robot grasping and transport without specialized hardware remain limited. This study introduces and experimentally validates a vision-guided, synchronized cooperative manipulation framework for two DJI RoboMaster EP mobile manipulators performing a cylindrical object pick-andplace task in warehouse-relevant settings. The key contribution of this work is an event-driven synchronization mechanism for dual-robot cooperative manipulation, which enables coordinated grasping and transport without direct robot-to-robot wireless messaging, depth sensors, external motion-capture infrastructure, or pre-built 3D maps. The manipulation pipeline includes visual lateral alignment, visual forward approach, grasp execution, synchronized lifting, cooperative transport, and coordinated release. Visual guidance is achieved using color-based HSV detection and proportional control, providing a lightweight perception and control solution for cooperative object handling. The framework is evaluated through fixed-position repeatability and position generalization studies. In a five-trial repeatability study, the system achieves a 100% task success rate with a mean completion time of 65.26 ±1.65 s and coefficient of variation of 2.5%. In a six-configuration generalization study, the system achieves 100% success, with task completion times ranging from 50.8 s to 86.5 s. Across all eleven trials, the proposed scheme maintains safe and correct task progression. Grip synchronization latency increases with asymmetry in the robots’ approach distances, with symmetric and asymmetric configurations producing latencies ≤ 6 s and ≥ 22 s, respectively. Overall, event-driven synchronization offers a practical, lightweight coordination mechanism for cooperative dual-robot manipulation under controlled laboratory conditions, with minimal sensing and communication requirements.

Authors

Institutions

Publication Details

Published
2026-11-16
DOI
https://doi.org/10.64589/juri/231576
Primary Topic
Robot Manipulation and Learning
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Vision-Guided Cooperative Manipulation Framework for Synchronized Grasping and Transport of Cylindrical Objects Using Dual Mobile Manipulators

Muhammad Faizan Mysorewala, Mohammed Abdel-Nasser, Muteb Hojayj Aljohani
1 links
Robot Manipulation and Learning
article

Vision-Guided Cooperative Manipulation Framework for Synchronized Grasping and Transport of Cylindrical Objects Using Dual Mobile Manipulators

Muhammad Faizan Mysorewala, Mohammed Abdel-Nasser, Muteb Hojayj Aljohani
article en

Abstract

Despite advances in cooperative mobile manipulation, reports on low-cost frameworks that enable dual-robot grasping and transport without specialized hardware remain limited. This study introduces and experimentally validates a vision-guided, synchronized cooperative manipulation framework for two DJI RoboMaster EP mobile manipulators performing a cylindrical object pick-andplace task in warehouse-relevant settings. The key contribution of this work is an event-driven synchronization mechanism for dual-robot cooperative manipulation, which enables coordinated grasping and transport without direct robot-to-robot wireless messaging, depth sensors, external motion-capture infrastructure, or pre-built 3D maps. The manipulation pipeline includes visual lateral alignment, visual forward approach, grasp execution, synchronized lifting, cooperative transport, and coordinated release. Visual guidance is achieved using color-based HSV detection and proportional control, providing a lightweight perception and control solution for cooperative object handling. The framework is evaluated through fixed-position repeatability and position generalization studies. In a five-trial repeatability study, the system achieves a 100% task success rate with a mean completion time of 65.26 ±1.65 s and coefficient of variation of 2.5%. In a six-configuration generalization study, the system achieves 100% success, with task completion times ranging from 50.8 s to 86.5 s. Across all eleven trials, the proposed scheme maintains safe and correct task progression. Grip synchronization latency increases with asymmetry in the robots’ approach distances, with symmetric and asymmetric configurations producing latencies ≤ 6 s and ≥ 22 s, respectively. Overall, event-driven synchronization offers a practical, lightweight coordination mechanism for cooperative dual-robot manipulation under controlled laboratory conditions, with minimal sensing and communication requirements.

Vol. 2(3B)
King Fahd University of Petroleum and Minerals (SA)
Robot Manipulation and Learning
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon