State-Based Disassembly Planning
Authors: Chao Lei, Nir Lipovetzky, Krista A. Ehinger
AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our experiments show that SBDP with new evaluation functions and DBGs constraints outperforms the stateof-the-art in disassembly planning in terms of success rate and computational efficiency over benchmark datasets consisting of thousands of physically valid industrial assemblies. |
| Researcher Affiliation | Academia | Chao Lei, Nir Lipovetzky, Krista A. Ehinger School of Computing and Information Systems, The University of Melbourne, Australia EMAIL, EMAIL |
| Pseudocode | Yes | Algorithm 1: SBDP |
| Open Source Code | No | The paper does not provide a direct link to a source-code repository, an explicit statement of code release, or mention code in supplementary materials for the methodology described. |
| Open Datasets | Yes | Tian et al. (2022) introduced a large-scale dataset comprising thousands of physically valid industrial assemblies, with comprehensive geometric pre-processed data for collision detection. |
| Dataset Splits | Yes | We catergorize assemblies consisting of 3-9 (small), 10-49 (medium), and 50+ (large) components as disassembly benchmarks, with 4196 problems in total. We denote PDPt and PDPr as PDP with translational or rotational motion, respectively. |
| Hardware Specification | Yes | All experiments were conducted on a cloud computer with clock speeds of 2.00 GHz Xeon processors and processes time out after 2 hours. |
| Software Dependencies | No | The paper mentions using a physics-based simulation built upon a rigid body simulator developed by Xu et al. (2021) and refers to methodologies like RRT (La Valle 1998) and Signed Distance Field (SDF), but it does not specify version numbers for any software libraries, programming languages, or specific tools used in their implementation. |
| Experiment Setup | Yes | All experiments were conducted on a cloud computer with clock speeds of 2.00 GHz Xeon processors and processes time out after 2 hours. In PDP , both translational and rotational search procedures are allotted 2 hours each. Physical simulation is restricted to 360 seconds to prevent endless execution. |