Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates.
Zeta*-SIPP: Improved Time-Optimal Any-Angle Safe-Interval Path Planning
Authors: Yiyuan Zou, Clark Borst
IJCAI 2024 | Venue PDF | LLM Run Details | Input Tokens: 16,321 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 3,526 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Benchmark experiments showed that Zeta*-SIPP reduced the computation time of TO-AA-SIPP by around 70%-90% on average. |
| Researcher Affiliation | Academia | Yiyuan Zou , Clark Borst Control and Simulation, Faculty of Aerospace Engineering Delft University of Technology, The Netherlands |
| Pseudocode | Yes | The pseudocode of Zeta-SIPP is shown in Algorithms 1-5. |
| Open Source Code | Yes | Our implementation is available at https://github.com/yiyuanzou/zeta-sipp. |
| Open Datasets | Yes | We performed experiments on three different benchmark maps [Stern et al., 2019]: Random-64-64-10, a 64 64 map with 10% of randomly blocked grids; Warehouse-10-20-102-2, a 170 84 map from a logistics domain; Berlin 1 256, a 256 256 real-world city map. |
| Dataset Splits | No | For each map, 500 scenarios were generated by the following steps: 1) Chose 25 benchmark scenario sets (random) [Stern et al., 2019]. 2) For each scenario set, we took the last 20 scenarios as tests and the top 32/64/96/128 scenarios as dynamic obstacles. The paper defines test scenarios but does not explicitly mention distinct training or validation splits in the context of model training. |
| Hardware Specification | Yes | All the algorithms were implemented in Java Script and the experiments were performed on Node.js v18.14.2 on a laptop with 2.30GHz Intel Core i7-11800H and 16 GB RAM. |
| Software Dependencies | Yes | All the algorithms were implemented in Java Script and the experiments were performed on Node.js v18.14.2 |
| Experiment Setup | Yes | For each map, 500 scenarios were generated by the following steps: 1) Chose 25 benchmark scenario sets (random) [Stern et al., 2019]. 2) For each scenario set, we took the last 20 scenarios as tests and the top 32/64/96/128 scenarios as dynamic obstacles. 3) The trajectories of dynamic obstacles were generated successively by Zeta*-SIPP, which were collision-free and contained any-angle moves. |