Embodied Intelligence in Disassembly: Multimodal Perception Cross-validation and Continual Learning in Neuro-Symbolic TAMP

2025-09-14

AI Summary

To address insufficient robotic perception robustness in unstructured, dynamic environments during battery pack disassembly of new-energy vehicles, this paper proposes an embodied intelligent continual learning framework integrating neural-symbolic reasoning with task-and-motion planning (TAMP). The framework incorporates a multimodal perception cross-validation mechanism and a bidirectional reasoning process: forward reasoning optimizes real-time action policies, while backward reasoning continually assimilates historical task data to enable system self-adaptation and evolution. By establishing a closed-loop perception–decision–execution architecture, the framework significantly enhances autonomous disassembly capability in complex industrial settings. Experimental results demonstrate a task success rate improvement from 81.68% to 100%, and a reduction in average perception misclassification instances from 3.389 to 1.128, validating substantial advances in both robustness and generalization.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Neuro-Symbolic Learning
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

With the rapid development of the new energy vehicle industry, the efficient disassembly and recycling of power batteries have become a critical challenge for the circular economy. In current unstructured disassembly scenarios, the dynamic nature of the environment severely limits the robustness of robotic perception, posing a significant barrier to autonomous disassembly in industrial applications. This paper proposes a continual learning framework based on Neuro-Symbolic task and motion planning (TAMP) to enhance the adaptability of embodied intelligence systems in dynamic environments. Our approach integrates a multimodal perception cross-validation mechanism into a bidirectional reasoning flow: the forward working flow dynamically refines and optimizes action strategies, while the backward learning flow autonomously collects effective data from historical task executions to facilitate continual system learning, enabling self-optimization. Experimental results show that the proposed framework improves the task success rate in dynamic disassembly scenarios from 81.68% to 100%, while reducing the average number of perception misjudgments from 3.389 to 1.128. This research provides a new paradigm for enhancing the robustness and adaptability of embodied intelligence in complex industrial environments.

Problem

• Enhancing robotic perception robustness in unstructured disassembly environments
• Improving autonomous disassembly through multimodal perception cross-validation
• Enabling continual self-optimization in neuro-symbolic task planning systems

Innovation

• Neuro-Symbolic TAMP framework
• Multimodal perception cross-validation
• Continual bidirectional learning flow