Revolutionizing Battery Disassembly: The Design and Implementation of a Battery Disassembly Autonomous Mobile Manipulator Robot(BEAM-1)

TL;DR

BEAM-1 tackles autonomous disassembly of end-of-life EV batteries in dynamic environments by fusing NeuralSymbolic AI with neural predicates, LLM-guided heuristic planning, and intuition-inspired motion sampling. It perceives state with neural predicates, plans primitive sequences via an LLM-enhanced tree search, and executes with high-precision action primitives on a four-level hardware-execution-task-motion architecture. The approach achieves high success rates across multiple bolt types and complex scenarios while supporting continuous learning across perception, planning, and motion components. This work provides a portable framework for embodied intelligent robots with autonomous reasoning and learning, with practical implications for green manufacturing and circular economy.

Abstract

The efficient disassembly of end-of-life electric vehicle batteries(EOL-EVBs) is crucial for green manufacturing and sustainable development. The current pre-programmed disassembly conducted by the Autonomous Mobile Manipulator Robot(AMMR) struggles to meet the disassembly requirements in dynamic environments, complex scenarios, and unstructured processes. In this paper, we propose a Battery Disassembly AMMR(BEAM-1) system based on NeuralSymbolic AI. It detects the environmental state by leveraging a combination of multi-sensors and neural predicates and then translates this information into a quasi-symbolic space. In real-time, it identifies the optimal sequence of action primitives through LLM-heuristic tree search, ensuring high-precision execution of these primitives. Additionally, it employs positional speculative sampling using intuitive networks and achieves the disassembly of various bolt types with a meticulously designed end-effector. Importantly, BEAM-1 is a continuously learning embodied intelligence system capable of subjective reasoning like a human, and possessing intuition. A large number of real scene experiments have proved that it can autonomously perceive, decide, and execute to complete the continuous disassembly of bolts in multiple, multi-category, and complex situations, with a success rate of 98.78%. This research attempts to use NeuroSymbolic AI to give robots real autonomous reasoning, planning, and learning capabilities. BEAM-1 realizes the revolution of battery disassembly. Its framework can be easily ported to any robotic system to realize different application scenarios, which provides a ground-breaking idea for the design and implementation of future embodied intelligent robotic systems.

Figures (8)

• Figure 1: System architecture of our BEAM-1. According to different functions, it can be categorized into (a) body composition-Hardware level, (b) intuition-guided motion sampling algorithm-Motion level, (c) predicate and primitive-based high precision control-Execution level, and (d) LLM-heuristic tree-searching task planning-Task level.
• Figure 2: Active and passive compliance end-effector.
• Figure 3: Quick-change disk with 20 different types of sleeves.
• Figure 4: Implementation process of the primitive Mate: Kalman filtering and other algorithms to ensure the high accuracy of the primitive.
• Figure 5: Reasoning engine with three prompting Sub-Engines based on LLM.