REGNav: Room Expert Guided Image-Goal Navigation
Authors: Pengna Li, Kangyi Wu, Jingwen Fu, Sanping Zhou
AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments show that our REGNav surpasses prior state-of-the-art works on three popular benchmarks. ... Experiments Dataset and evaluation metric. We conduct all of the experiments on the Habitat simulator (Savva et al. 2019; Szot et al. 2021). We train our agent on the Gibson dataset (Xia et al. 2018) ... We test our agent on the Matterport 3D (Chang et al. 2017) and Habitat Matterport 3D dataset (Ramakrishnan et al. 2021) to validate the cross-domain generalization ability of our agent. For evaluation, we utilize the Success Rate (SR) and Success Weighted by Path Length (SPL) (Anderson et al. 2018a). ... Ablation study on Room Expert training scheme. ... Comparison of different fusion manners. ... Visualization. |
| Researcher Affiliation | Academia | Institute of Artificial Intelligence and Robotics, Xi an Jiaotong University EMAIL, EMAIL |
| Pseudocode | No | The paper describes methods using equations and textual descriptions, but no explicit pseudocode or algorithm blocks are provided. |
| Open Source Code | Yes | Code https://github.com/leeBooMla/REGNav |
| Open Datasets | Yes | We conduct all of the experiments on the Habitat simulator (Savva et al. 2019; Szot et al. 2021). We train our agent on the Gibson dataset (Xia et al. 2018) ... We test our agent on the Matterport 3D (Chang et al. 2017) and Habitat Matterport 3D dataset (Ramakrishnan et al. 2021) |
| Dataset Splits | Yes | We train our agent on the Gibson dataset (Xia et al. 2018) with the dataset split provided by (Mezghan et al. 2022). The dataset provides diverse indoor scenes, consisting of 72 training scenes and 14 testing scenes. ... Mem-Aug categorized the test episodes of Gibson into three levels of difficulty We evaluate our REGNav on the corresponding set and report the results in Table 2. our proposed method illustrates superior performance, outperforming the memory-based meth- |
| Hardware Specification | Yes | For navigation learning, we train our REGNav for 500M steps on 8 3090 GPUs. |
| Software Dependencies | No | The paper mentions several models and frameworks like ResNet-50, ImageNet, SAM, Adam optimizer, GRU, but does not provide specific version numbers for any software dependencies required to reproduce the experiments. |
| Experiment Setup | Yes | For the pre-training stage, we use the Adam optimizer with weight decay 5e-4 and batch size 64 to train the style encoder and relation network for 20 epochs. We set the refinement hyper-parameter γ as an adaptive parameter. ... We set the balance parameter ω equal to 1. For navigation learning, we train our REGNav for 500M steps on 8 3090 GPUs. Other hyperparameters follow the ZER. ... The height of agent is set to 1.5m and the radius is 0.1m. The agent has a single RGB sensor with a 90 FOV and 128 128 resolution. The action space consists of MOVE FORWARD by 0.25m, TURN LEFT, TURN RIGHT by 30 and STOP. ... In an episode, the success distance is within 1m and the maximum steps are set to 500. |