Learning from Planned Data to Improve Robotic Pick-and-Place Planning Efficiency

2025-06-18

AI Summary

To address the low efficiency of shared grasp planning in robotic pick-and-place tasks, this paper proposes an energy-based shared grasp prediction method. We first formally define and model shared grasp feasibility across both initial and target object poses, introducing an energy-coupling mechanism that jointly evaluates grasp energies across multiple poses—replacing conventional independent binary classification and thereby substantially reducing the search space. Our approach is built upon an Energy-Based Model (EBM), integrating physical constraints with data-driven learning to enable efficient and generalizable joint modeling of grasp feasibility. Experiments demonstrate strong generalization to unseen grasps and objects with similar shapes, achieving significant improvements in grasp selection accuracy. Moreover, the method improves data efficiency by approximately 40% and reduces planning computational overhead by over 60%.

Technology Category

• Intelligent Robots: Manipulation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Economics, Online Markets and Human Computation: The sharing economy
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

This work proposes a learning method to accelerate robotic pick-and-place planning by predicting shared grasps. Shared grasps are defined as grasp poses feasible to both the initial and goal object configurations in a pick-and-place task. Traditional analytical methods for solving shared grasps evaluate grasp candidates separately, leading to substantial computational overhead as the candidate set grows. To overcome the limitation, we introduce an Energy-Based Model (EBM) that predicts shared grasps by combining the energies of feasible grasps at both object poses. This formulation enables early identification of promising candidates and significantly reduces the search space. Experiments show that our method improves grasp selection performance, offers higher data efficiency, and generalizes well to unseen grasps and similarly shaped objects.

Problem

• Accelerate robotic pick-and-place planning via shared grasps prediction
• Reduce computational overhead in grasp candidate evaluation
• Improve grasp selection performance and data efficiency

Innovation

• Energy-Based Model predicts shared grasps
• Combines grasp energies for efficiency
• Reduces search space significantly