Synthesizing Multi-Log Grasp Poses in Cluttered Environments
Authors:
- Arvid FälldinAFArvid Fälldin
- Tommy LöfstedtTLTommy Löfstedt
- Tobias SembergTSTobias Semberg
- Erik WallinEWErik Wallin
- Martin ServinMSMartin Servin
Open Access
- 25 April 2026
- journal article
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 112 (2)
Abstract
Multi-object grasping is a challenging task. It is important for energy and cost-efficient operation of industrial crane manipulators, such as those used to collect tree logs from the forest floor and on forest machines. In this work, we used synthetic data from physics simulations to explore how data-driven modeling can be used to infer multi-object grasp poses from images. We showed that convolutional neural networks can be trained specifically for synthesizing multi-object grasps. Using RGB-Depth images and instance segmentation masks as input, a U-Net model outputs grasp maps with the corresponding grapple orientation and opening width. Given an observation of a pile of logs, the model can be used to synthesize and rate the possible grasp poses and select the most suitable one, with the possibility to respect changing operational constraints such as lift capacity and reach. When tested in simulation on previously unseen data, the proposed model found successful grasp poses with an accuracy of up to 96%.Keywords
All Related Versions
Funding Information
- Mistra Digital Forest (DIA 2017/14 #6)
This publication has 22 references indexed in Scilit:
- Towards Autonomous Wood-Log Grasping with a Forestry Crane: Simulator and Benchmarking2025
- Log Loading Automation for Timber-Harvesting Industry2024
- Exploring the feasibility of autonomous forestry operations: Results from the first experimental unmanned machineJournal of Field Robotics, 2024
- Segment Anything2023
- Grasp Planning with CNN for Log-loading Forestry Machine2023
- Multi-object Grasping in the Plane2023
- End-to-end Trainable Deep Neural Network for Robotic Grasp Detection and Semantic Segmentation from RGB2021
- RL-CycleGAN: Reinforcement Learning Aware Simulation-to-Real2020
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Efficient grasping from RGBD images: Learning using a new rectangle representation2011