A Goal Reasoning Agent for Controlling UAVs in Beyond-Visual-Range Air Combat
Authors: Michael W. Floyd, Justin Karneeb, Philip Moore, David W. Aha
IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We describe evidence from our empirical study that the TBM significantly outperforms an expert-scripted agent in BVR scenarios. We also report the results of an ablation study which indicates that all components of our agent architecture are needed to maximize mission performance. |
| Researcher Affiliation | Collaboration | Michael W. Floyd1 and Justin Karneeb1 and Philip Moore1 and David W. Aha2 1Knexus Research Corporation; Springfield, Virginia; USA 2Navy Center for Applied Research in AI; Naval Research Laboratory; Washington, DC; USA |
| Pseudocode | No | The paper describes the system design with text and a conceptual diagram (Figure 1), but does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described, nor does it state that the code is open-source. |
| Open Datasets | No | The paper states, 'We use the Advanced Framework for Simulation, Integration and Modeling (AFSIM) system [Clive et al., 2015], a high-fidelity air combat simulator that allows aircraft to be controlled either programmatically or using physical hardware...' and 'The prototypical scenario was used to create 100 different random scenarios...'. This describes the use of a simulator to generate scenarios for evaluation, not a publicly available, fixed dataset with access information. |
| Dataset Splits | No | The paper describes the creation of 100 random scenarios and 200 total runs for evaluation but does not specify train/validation/test dataset splits. The TBM is evaluated on these scenarios, rather than being trained or validated on specific data splits. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments, only mentioning the use of a high-fidelity air combat simulator (AFSIM). |
| Software Dependencies | No | The paper mentions the use of 'Advanced Framework for Simulation, Integration and Modeling (AFSIM) system [Clive et al., 2015]' but does not provide a specific version number for AFSIM or any other ancillary software libraries or frameworks used in the implementation of the TBM. |
| Experiment Setup | No | The paper describes the experimental conditions, scenario setup (e.g., 4 vs 4 aircraft, initial spacing), and metrics used. It also describes some rule-based components and mentions 'thresholds' (e.g., for distance in Goal Manager rules), but it does not provide specific numerical values for these thresholds or any other concrete hyperparameters or system-level training settings needed for full reproducibility of the agent's internal configuration. |