Cooperative Grasping for Collective Object Transport in Constrained Environments

2025-09-03

AI Summary

This paper addresses the feasibility assessment problem for dual-robot collaborative grasping and collective transport in constrained environments. We propose a conditional-embedding-based decision framework that jointly encodes grasp configurations and environmental constraints—such as occupancy maps and object geometry—into a shared latent space, modeling their implicit mapping via a conditional embedding network. To enhance discriminative capability, we introduce a negative sampling–based supervised learning strategy, significantly improving both classification accuracy between feasible and infeasible configurations and cross-scenario generalization. Extensive experiments in simulation and on real robotic platforms demonstrate that the model reliably identifies valid grasps across diverse environments and object geometries, confirming its effectiveness, robustness, and practical deployability. The core contribution lies in the first systematic application of conditional embedding to feasibility reasoning for multi-robot collaborative manipulation.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Natural Language Processing: Safety and Robustness
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

We propose a novel framework for decision-making in cooperative grasping for two-robot object transport in constrained environments. The core of the framework is a Conditional Embedding (CE) model consisting of two neural networks that map grasp configuration information into an embedding space. The resulting embedding vectors are then used to identify feasible grasp configurations that allow two robots to collaboratively transport an object. To ensure generalizability across diverse environments and object geometries, the neural networks are trained on a dataset comprising a range of environment maps and object shapes. We employ a supervised learning approach with negative sampling to ensure that the learned embeddings effectively distinguish between feasible and infeasible grasp configurations. Evaluation results across a wide range of environments and objects in simulations demonstrate the model's ability to reliably identify feasible grasp configurations. We further validate the framework through experiments on a physical robotic platform, confirming its practical applicability.

Problem

• Cooperative grasping for two-robot object transport in constrained environments
• Identifying feasible grasp configurations for collaborative object transportation
• Ensuring generalizability across diverse environments and object geometries

Innovation

• Conditional Embedding model with neural networks
• Supervised learning with negative sampling
• Generalizable across environments and objects