Many-Objective-Optimized Semi-Automated Robotic Disassembly Sequences

TL;DR

This work tackles many-objective disassembly sequence planning (DSP) for semi-automated robotics by developing a NSGA-III-inspired MaOGA that optimizes feasibility, stability, and four CAD-derived objectives (difficulty, efficiency, prioritization, allocability). It fuses CAD-informed matrices with a contact/connection graph (CCG) and a CCD-based initialization to produce repeatable, constraint-satisfied initial solutions, then refines them via non-dominated sorting and reference-line niching. Experiments on a 36-part belt drive unit demonstrate 100% feasibility and stability with sequences that are practically realizable by a 7-DoF robot using multiple end-effectors and soft-jigs, underscoring the approach’s potential for semi-automated robotic DSP. The methodology advances DSP by embedding robot-motion feasibility into the optimization loop and suggesting avenues for automatic labeling, real-world deployment, and HRC-oriented extensions.

Abstract

This study tasckles the problem of many-objective sequence optimization for semi-automated robotic disassembly operations. To this end, we employ a many-objective genetic algorithm (MaOGA) algorithm inspired by the Non-dominated Sorting Genetic Algorithm (NSGA)-III, along with robotic-disassembly-oriented constraints and objective functions derived from geometrical and robot simulations using 3-dimensional (3D) geometrical information stored in a 3D Computer-Aided Design (CAD) model of the target product. The MaOGA begins by generating a set of initial chromosomes based on a contact and connection graph (CCG), rather than random chromosomes, to avoid falling into a local minimum and yield repeatable convergence. The optimization imposes constraints on feasibility and stability as well as objective functions regarding difficulty, efficiency, prioritization, and allocability to generate a sequence that satisfies many preferred conditions under mandatory requirements for semi-automated robotic disassembly. The NSGA-III-inspired MaOGA also utilizes non-dominated sorting and niching with reference lines to further encourage steady and stable exploration and uniformly lower the overall evaluation values. Our sequence generation experiments for a complex product (36 parts) demonstrated that the proposed method can consistently produce feasible and stable sequences with a 100% success rate, bringing the multiple preferred conditions closer to the optimal solution required for semi-automated robotic disassembly operations.

Figures (22)

• Figure 1: NSGA-III-inspired sequence optimization.
• Figure 2: Contact and connection graph (CCG).
• Figure 3: An example of the generated initial solution.
• Figure 5: Robotic disassembly setup for simulation experiments.
• Figure 6: Model appearance and assigned parts labels.